Project Showcase

AI-Powered First-Line Support Agent (RAG)

AI Engineer

The project involved developing an intelligent automation system to handle Tier-1 customer inquiries for a microsite building platform. By leveraging advanced Retrieval-Augmented Generation (RAG), the system analyzes a knowledge base of over 280 articles to provide instant and accurate responses. The solution was designed to solve scalability challenges by automating repetitive, low-complexity questions that previously overwhelmed the human support team.

AI Agents Management & Orchestration Control Plane

AI Engineer

Developed a centralized, production-grade management platform (Control Plane) for the lifecycle management of specialized AI agents. The system provides a unified web interface for defining agent personas, deploying them across diverse environments, and monitoring their performance and token consumption in real-time.

AI-Powered Multi-Modal City Guide

AI Lead Engineer

Architected and launched a mobile-first, multi-modal AI travel companion that generates dynamic, location-aware storytelling. The platform utilizes generative AI to create historical narratives for points of interest, translates content in real-time, and synthesizes high-quality audio guides for a hands-free user experience.

Multi-Agent Personal Assistant & Time Organizer

AI Engineer

The project involved building a sophisticated personal productivity automation system based on a Multi-Agent Architecture to streamline tasks and professional collaboration. The system integrates with Google Workspace, Jira, Zoom, and Confluence to provide unified task management, automated scheduling, and intelligent email triage. By using a Supervisor Agent to orchestrate specialized sub-agents, the platform autonomously handles complex workflows like research and meeting coordination while maintaining human-in-the-loop security.

AI-Powered Creative Automation System

Lead AI Engineer / Architect

Creative teams lose days on manual marketing asset production, with inconsistent brand use, multi-platform resizing, and weak product-identity control. The system automates the pipeline from brief to delivery: it uses Computer Vision for design analysis, automated prompt engineering, fine-tuned generative models, smart one-to-many resizing (Saliency Maps), and ControlNet for product fidelity, with automated brand and compliance checks—cutting production from days to minutes while keeping full brand consistency.

Interrogation Transcription System for Law Enforcement

Voice AI Engineer

Automated real-time transcription of interviews to generate official protocols in a secure environment. On-premise (air-gapped) deployment ensuring maximum security and data privacy. Core Model: Python, OpenAI Whisper, Pyannote, Docker, on-premise deployment Orchestration: Custom system for real-time processing (voice detection + chunking + transcription). Supports up to 10 simultaneous sessions. Fine-tuning Pipeline: Created a pipeline for periodic model updates using client-provided datasets (edited transcripts). Focused on adapting to (local dialect) and low-quality audio. Metrics: Used WER (Word Error Rate) and CER (Character Error Rate) to validate model performance. Deployment: On-premise (Air-gapped). All components are deployed locally to ensure maximum security and data privacy.

Financial Voice Agent for Call Center

Voice AI Engineer

Voice agent integration for a financial services company with a focus on mobile stability. Focus: Integrated AI agents with telephony infrastructure. Solved architectural challenges regarding vendor integrations. Performance: Focused on maintaining high communication quality over mobile networks.

RAG for Medical equipment marketplace

AI Engineer

Knowledge base system for medical device documentation with semantic search capabilities. Pipeline: Web scraping of manufacturer manuals for specified medical devices → chunking → indexing with metadata → storage in vector database. Core Functionality: On query, retrieves relevant documentation and specifications for a given medical device.

Deepfake Voice Detection System

AI Solutions Architect

Telecom providers and financial institutions needed a solution to detect synthetic speech and protect against voice fraud in call centers. We built a real-time deepfake detection system for streaming audio using speaker recognition, diarization, ASR, Deep Fake detector model.

Fruit Counting System for Agricultural Robotics

Computer Vision Engineer

Farmers and agri-tech companies required automated fruit yield estimation to plan harvest and optimize logistics. Designed a robotic vision system to count oranges on trees using 3D cameras, depth sensors, and GPS.

AI Audio Summarization & Call Analysis

AI Voice Engineer

Call center teams and financial services wanted faster review of long customer calls for compliance and support optimization. Built an AI-powered system for speech-to-text transcription, speaker separation, and intelligent summarization of conversations.

Generative AI Video Platform (Lipsync & Video Generation)

Senior Deep Learning Research Engineer

Development of a large-scale generative AI video platform serving high-volume content creation, architecting image-to-video and video-to-video systems from scratch.

Image Generation Service based

Computer Vision Researcher

Built a scalable production image generation service based on Stable Diffusion capable of handling user-level traffic.

AI-Based Fitness Technique Correction App

Computer Vision Engineer

Developed a real-time fitness application that analyzes exercise technique using a camera. Users select an exercise, position the camera, and receive feedback on movement correctness.

Real-Time Football Match Perception System

Computer Vision Engineer

Led the end-to-end development of a real-time computer vision system for football match analytics, combining OCR, object detection, tracking, classification, and classical CV techniques into a unified production pipeline.

Smart Parking Detection System

Computer Vision Engineer

Designed a system that detects available parking spaces from live camera feeds.

AI-Driven Campaign Optimization Platform

Lead Data Scientist / ML Engineer

A telecom company had large volumes of messaging and campaign data but no practical way to use it for targeting or personalization. The goal was to build production ML systems that could directly improve campaign performance.

Live Streaming Reinforcement Learning Recommendation System

Lead AI Engineer / Architect

A consumer-facing live streaming platform needed to improve real-time content recommendations under strict latency constraints. Traditional offline-trained models were slow to adapt to user behavior and changing content dynamics. The goal was to design a system that could learn continuously from live user interactions.

Quantitative Research Infrastructure Optimization

Data / Platform Architect

A crypto investment fund needed to run large-scale backtests over long historical time ranges. An initial cloud-first design using managed services proved too expensive once realistic workloads were tested.

URLs Scraping Pipeline

Data Engineer / Backend Engineer

Built an end-to-end URL scraping high-throughput platform to continuously discover, schedule, and scrape web pages at scale. The pipeline coordinates scraping demand, executes distributed scraping jobs, and emits structured outputs for downstream processing and monitoring.

Kubernetes Autoscaling & Capacity Optimization

Cloud / Platform Engineer (AWS EKS / Karpenter)

Built and maintained AWS EKS node provisioning with Karpenter by defining scalable, workload-aware node pools to automatically right-size capacity and improve cluster elasticity for data/compute services.

Databricks Lakehouse Ingestion & Medallion Architecture

Data Engineer

Built and operated a Databricks Lakehouse ingestion and transformation framework on Delta Lake, implementing a Medallion Architecture (Bronze/Silver/Gold) to move data from raw landing through curated layers into analytics-ready datasets for reporting and KPI consumption.

High-Load Enterprise Ingestion & Inference Platform

AI Lead Engineer

Led the architecture and development of a scalable, multi-tenant RAG (Retrieval-Augmented Generation) platform designed to ingest and index massive volumes of heterogeneous enterprise data. The system enables automated monitoring of client-defined storage, transforming unstructured data into a queryable knowledge base powered by a variety of Large Language Models.

No-Code Knowledge Ingestion & Semantic Search

AI Engineer

Engineered a lightweight, no-code RAG solution to bridge the gap between static cloud storage and interactive AI. The system monitors Google Drive directories, automatically ingesting newly uploaded documents of various formats into a vector database to enable natural language querying.

AI-Powered Natural Language Interface for DevOps Monitoring

AI Engineer

Telecom providers and financial institutions needed a solution to detect synthetic speech and protect against voice fraud in call centers. We built a real-time deepfake detection system for streaming audio using speaker recognition, diarization, ASR, Deep Fake detector model. Management needs monitoring data for decisions but has no SQL skills, so they depend on DevOps for every request and wait 1–2 hours while engineers spend 20–30% of their time on routine data pulls. An AI assistant in Slack lets users ask questions in plain English, turns them into read-only database queries with full audit trails, and escalates when unsure—cutting DevOps time on data requests by 60–80% and giving near-instant, self-service access to system performance, costs, and errors.

AI-Powered Credit Card Competitive Intelligence System

AI Engineer

Financial institutions were manually monitoring 500+ pages across 15+ comparison sites every day, and traditional scrapers kept breaking whenever site layouts changed. The solution is a self-healing AI platform that uses semantic HTML analysis (81.82% accuracy), adaptive parsing (98% success rate), and automated analytics to collect and analyze competitive data, adapt to site changes in hours, and turn raw data into trend analysis and strategic recommendations.

OCR & Document translation pipeline

AI Engineer

Automated document processing system for extracting structured data from diverse file formats and translating into target languages. Input: PDF, images, DOCX, TXT and other file formats. Core Pipeline: File ingestion → OCR extraction (Qwen2.5-VL) → structured JSON output for rendering → translation to target language (Gemma 3).

Automated Generation of Dental Treatment Plans with LLM and RAG

AI Project Lead

The project involved designing and implementing an AI system for automated generation of dental treatment plans by combining classical machine learning, Retrieval-Augmented Generation (RAG), and large language models (LLM). The solution was developed around medical datasets, doctor-validated clinical rules, and human-in-the-loop feedback to improve quality, safety, and practical adoption in clinical workflows.

Demand Forecasting & Auto-Replenishment System (TFT)

The project involved developing an AI-driven demand forecasting system for a large network of distributed retail locations (scalable to thousands). The solution enabled fully automated inventory replenishment by predicting product demand for fast-moving SKUs across all categories (food, beverages, non-food). The system addressed inefficiencies in manual ordering processes, preventing both stockouts and overstock. Technical details: Forecast horizon: aligned with operational constraints (e.g., delivery cycles) Error metric: MAPE (baseline: simple average-based forecasting) Clustering: HDBSCAN on behavioral patterns Inference mode: batch (triggered by operational events)

Sleep Disorders Prediction from Biosignals and Clinical Data

Data Scientist / Medical Researcher

The project involved leading a scientific data science initiative focused on early detection of sleep disorders using real-time biosignals and clinical data. The solution was designed to support improved diagnostic insights by combining advanced healthcare analytics, signal processing, and machine learning with clinically relevant interpretation. The work integrated multiple biomedical data sources to identify meaningful patterns associated with sleep disorders.

Remote Vitals Tracking and Stress Detection from Facial Video

Research Engineer (R&D) / Data Scientist / Applied Scientist / Subject-Matter Expert

The project involved leading the scientific research and development of a camera-based health monitoring solution for remote vital signs tracking and stress detection. The system was designed to extract physiological signals directly from facial video and support health and wellness applications through non-contact monitoring. The work combined medical research, signal processing, healthcare analytics, and machine learning to build scalable algorithms for real-world device environments.

Nutrigenomics Disease Prevention Platform

Research Engineer / Bioinformatician / Data Scientist / Applied Scientist / SME

The project involved developing a scientific and analytical framework for disease prevention based on nutrigenomics, integrating genetic, biochemical, lifestyle, and biobank data. The solution aimed to generate personalized health recommendations and identify disease risks through combined bioinformatics, predictive analytics, and healthcare data science methods.

Healthcare AI for Detecting Cardiac Diseases from Biomedical Signals and Images

Research Engineer / Data Scientist / Applied Scientist / SME

The project involved scientific research and development of AI algorithms for detecting cardiovascular diseases from biomedical signals, medical images, and biobank data. The work covered end-to-end research design, experimentation, and algorithm development for healthcare applications, including cardiac image analysis and predictive models derived from physiological data.

AI Support Agent with Self-Learning Loop

AI support agent automating Tier-1 customer support across chat-based channels (web, mobile, etc.), handling hundreds of thousands of tickets annually. Technical details: Automation metric: AI-handled vs total tickets Agent scope: full conversation handling (classification, resolution, escalation) Embeddings: locally hosted models Summarization: locally hosted models Clustering: HDBSCAN Vector DB: Qdrant

Embedded Computer Vision Pipeline for Edge Device

AI Engineer

Developed an end-to-end Computer Vision pipeline to detect light bulb activity on industrial machines and generate operational statistics (working vs idle time). The system enabled automated reporting and provided actionable insights to improve machine efficiency and business decision-making.

Image Processing Pipelines for Cosmetic Brands

AI Engineer / MLOps Engineer

Worked on pipelines processing large-scale image data provided by cosmetic brands. The system required consistent validation and monitoring of incoming data to ensure quality across multiple datasets used for downstream AI models.

Security Red-Teaming & Adversarial Hardening for Frontier LLM Series

Security AI Engineer

The project provides specialized, project-based Senior ML Security Engineering consultation for Alibaba Group's proprietary LLM division. Operating within an airgapped, SCIF-level laboratory, the focus is adversarial robustness and operational security redteaming for frontier models. Alibaba's Qwen series began with the beta release in April 2023 under the name Tongyi Qianwen, with Qwen-7B open-sourced in August 2023 and Qwen-72B released in December 2023. The Qwen2 series launched in June 2024 with 72B parameters, Qwen3 followed in April 2025, and Qwen3-Coder was open-sourced in July 2025.

Real-time sentiment & volatility forecasting system for fintech

Senior Machine Learning Engineer

This project involved building a proprietary predictive intelligence platform for a Belgian fintech firm focused on cryptocurrency risk mitigation. The system was engineered as a loss-prevention agent designed to forecast negative market shocks by triangulating over 400 heterogeneous data streams. LLMs were integrated into the sentiment pipeline using the most advanced models available during the project timeline: BERT (2018) for initial embedding work, followed by GPT-2 (staged release February–November 2019) and SentenceBERT (August 2019) for semantic similarity and panic classification

Behavioral analysis of personalization engines & dark patterns

Adversarial Machine Learning Engineer

The engagement involved a comprehensive adversarial audit of the TEMU mobile application's personalization engine, focusing on the intersection of privacy controls and behavioral psychology exploitation. The primary objective was to instrument the application to detect and classify a proprietary "Compulsive Spending Propensity Model" - an algorithmic layer designed to identify users exhibiting shopaholic or impulse-buying behavior patterns. LLMs were employed to semantically analyze ad copy and UI strings, leveraging models released during the project window: LLaMA 2 (July 2023) for initial prototyping, followed by Mistral 7B (September 2023) for production dark pattern classification.

Agentic Automation Platform for Document-Intensive Workflows

AI Architect & Tech Lead Data Engineer

The project involved architecting a greenfield agentic AI platform that automates the end-to-end processing of high-volume, document-heavy business cases for a regulated enterprise. A supervisor-style agent graph routes each case through a set of specialist agents that handle ingestion, enrichment, validation, coordination, and resolution, replacing manual review queues while keeping a human-in-the-loop checkpoint on high-stakes transitions. The agent layer sits on top of a cloud-native Databricks data platform with Unity Catalog governance, declarative streaming ingestion from an object-store landing zone, and a multi-region, multi-tenant infrastructure baseline.

AI-Driven Retail Execution Platform

Lead Data & ML Engineer

The project involved delivering an enterprise data and AI platform for a multinational consumer-goods company to orchestrate daily sales-execution planning for its field teams across several major retail channels and international markets. The platform combines a medallion-architecture lakehouse on Databricks with a portfolio of production ML models that translate raw retailer feeds, inventory signals, compliance data, and third-party audits into a ranked set of outlet-level tasks delivered to reps each morning. The system operates as a multi-tenant codebase where each retailer channel is onboarded as a configurable tenant rather than a fork.

Cloud Lakehouse with Change-Data-Capture Ingestion

Senior Data Engineer & Architect

The project involved designing and delivering a cloud-native data platform for a financial-services institution moving off a fragmented legacy ETL stack. The platform is built around a medallion lakehouse on Databricks, declarative streaming transformations for the silver layer, and log-based change-data-capture from operational relational sources via a managed Kafka service. A config-driven pipeline layer decouples table onboarding from code changes, and a data-quality engine splits each stream into a clean sink and a quarantine sink for audit and remediation.

Cloud Data Platform for Neobank

Senior Data Engineer

End-to-end cloud data platform for a fast-growing neobank, with core event tables ingesting large volumes of data daily and hundreds of terabytes of cumulative data. The platform underpins reconciliation, partner integrations, and financial reporting – operating on a cloud-managed infrastructure where both reliability and regulatory compliance are non-negotiable. Given the nature of the business, any pipeline failure or data discrepancy carries direct financial and audit consequences.

Multi-Asset Market Data Platform

Senior Data Engineer

Mission-critical market data platform covering equities across dozens of global exchanges, FX, and fixed income, serving both internal quantitative trading desks. At this scale and in this context, reliability is not a quality attribute – it is the product. The system had to sustain consistent ingestion and low-latency access during peak trading hours across multiple time zones, with no tolerance for data gaps or processing delays that could affect trading decisions.

Enterprise Data Warehouse Migration & Recommendation Systems

Senior Data Engineer

Data platform modernization for one of the largest US retail chains, spanning over a thousand physical stores and a major e-commerce operation. The scope covered legacy warehouse migration, recommendation pipeline rebuilding, and data governance implementation – all across a petabyte-scale environment without disrupting ongoing retail analytics.

Centralized Data Platform & Configuration-Driven Framework

Senior Big Data Engineer

Co-architected a configuration-driven unified abstract framework that abstracts heterogeneous data sources - HDFS, S3, Kafka, and Iceberg - behind a single declarative interface for a next-generation centralized data platform. The framework standardizes how dozens of teams build, deploy, and operate Spark pipelines, replacing fragmented per-team implementations with a consistent foundation that enforces best practices and shortens time-to-production.

Telecom BI Platform Migration to Hadoop

Big Data Engineer

The project involved migrating a legacy Oracle-based BI platform to a unified Hadoop-based solution for a major telecom company. The system supported ingestion and processing of TAP/RAP files containing telecom charging and tax data, while maintaining compatibility with existing Oracle ETL pipelines. The key challenge was improving scalability and processing efficiency while ensuring a smooth transition to a distributed data processing architecture.

Enterprise Retail Data Platform

Big Data Engineer

The project involved building and maintaining an enterprise-scale data platform for a global apparel and footwear company. The platform processed shopping and transactional data to deliver curated datasets for analytics, reporting, and business decision-making. It combined Spark-based batch processing, lightweight Lambda workflows, Redshift analytical transformations, and unified orchestration. In later phases, the platform was migrated from AWS-based pipelines to Azure Databricks as part of the company’s cloud modernization strategy.

Identity Verification Data Platform Modernization

Senior Big Data Engineer

The project involved modernizing a large-scale data processing platform used for identity validation, fraud detection, and analytical reporting. The system ingested data from external service providers and transformed it into reliable metrics for BI dashboards. A key part of the initiative was migrating the platform from Delta Lake to Apache Iceberg while preserving performance, stability, and cost efficiency. To reduce migration risk, a temporary dual-stack architecture was introduced, allowing Delta and Iceberg pipelines to run in parallel during the transition.

FinWhale Trading Platform

AI Engineer

The project involved designing and shipping FinWhale, an AI-native financial research platform that fuses a multi-tool conversational agent with structured market-data tools. The platform combines a streaming agent chat backed by LangGraph Cloud, a tabular Data Lens heatmap for cross-ticker quantitative analysis, candlestick Charts with bidirectional daily/intraday linking, and Custom ETF construction. The agent autonomously performs SEC EDGAR filing extraction, SQL queries against years of OHLC market history, web research, and Python execution inside isolated E2B sandboxes - turning hours of manual research into a single conversation.

FinWhale for Investment Bankers

Buyer Landscape Research & Outreach Agent

The project involved adapting FinWhale's multi-tool research agent into a vertical product for sell-side M&A advisors. Given a target company preparing for sale, the system autonomously maps the full buyer landscape - strategic acquirers and financial sponsors - scores each candidate on strategic fit, M&A capacity, and recency of activity, and generates ready-to-use outreach hooks tailored to each acquirer's stated strategy. Every claim and hook is grounded in citations from SEC filings, earnings transcripts, deal databases, and public news so the banker can paste a first-touch email into Outlook in minutes rather than spending two to three weeks staffing junior analysts.

AI-Powered Visual Product Search

AI / Cloud Engineer

Developed an image-based product search system for a major retail chain with 100K+ SKU catalog. Customers upload a product photo and instantly find matching items in stores. The solution uses a novel approach: LLM generates semantic descriptions from images, which are embedded and matched against the catalog via vector similarity search.

Enterprise Knowledge Base with Conversational AI Search

AI / Cloud Engineer

Built an AI-powered knowledge base for a large logistics company group (5 subsidiaries). The system syncs thousands of PDFs from Google Drive, indexes them in Vertex AI Search, and provides employees with conversational AI search - delivering answers with citations from corporate documentation.

Email Archive Processing & AI Search Pipeline

Cloud / AI Engineer

Built a distributed ETL platform for processing massive email archives (EML files in ZIP/7Z/RAR) into structured PDFs, uploading to Cloud Storage, and indexing in Vertex AI Search. 9 isolated workspaces with strict data separation - designed for a government organization.

Spark Pipeline Migration from YARN to Kubernetes

Senior Big Data Engineer

Modernization of mission-critical content-moderation data infrastructure for one of the world’s largest technology companies, migrating legacy Spark-on-YARN pipelines to a cloud-native Spark-on-Kubernetes platform. The initiative enables elastic scaling, reduces operational overhead, and aligns the data stack with the broader enterprise shift toward containerized infrastructure across thousands of services.

Delta Lake Migration & Auto-Scaling ETL Platform

Senior Data Engineer

End-to-end ownership of the data-exchange (DX) ETL platform on Databricks for a Tier-1 US telecom and media operator, supporting large-scale ingestion, transformation, and analytics workloads. The project encompassed migrating storage to Delta Lake for ACID guarantees, building auto-scaling compute infrastructure for volatile workloads, and automating operational tooling to reduce manual ops overhead across the data engineering team.

AI-Powered Agentic system for CUSO (Credit Union Service Organization)

AI Architect

The project involved developing multi-agentic system to handle credit union – related data and reports (based on AIRES data, CallReport and others). By leveraging advanced Retrieval-Augmented Generation (RAG), the system analyzes a knowledge base of over 10,000,000 lines of data to provide instant and accurate responses. The solution was designed to solve scalability challenges by support both well-structured and free-form reports and analysis.

Large-Scale Data Platform for AI-Driven Recruiting

Data Engineering Team Lead

WorkHQ is an AI-powered recruiting platform designed to help companies source, contact, and manage talent at scale. The project centred on architecting and scaling a production-grade data platform capable of ingesting, normalising, and serving nearly 1 billion candidate profiles sourced from multiple global data providers. The core engineering challenge was transforming an unstable, custom legacy infrastructure (AWS S3 + Airflow) into a reliable, high-throughput Lakehouse architecture capable of supporting real-time semantic search and AI-powered candidate matching across 7 global regions.

AI Recruiter - Intelligent Candidate Matching & Automated Recruitment Pipeline

Senior Data / Backend Engineer

As a sub-project within the WorkHQ platform, the AI Recruiter was built to automate and intelligently augment the end-to-end recruitment workflow for HR teams. The system allows recruiters to search for the best-matched candidates either through a conversational chat interface or by uploading a job vacancy file. It combines semantic vector search across hundreds of millions of profiles with OpenAI Reasoning models to surface and explain the most relevant candidates. Beyond matching, the system automates the full downstream recruitment funnel - from application emails and online assessment links to interview slot scheduling and outcome notifications - all orchestrated via serverless AWS infrastructure.

AI-Powered First-Line Support Agent (RAG)

AI Engineer

Developed an intelligent automation system to handle Tier-1 customer inquiries for a microsite building platform. By leveraging advanced Retrieval-Augmented Generation (RAG), the system analyzes a knowledge base of over 280 articles to provide instant and accurate responses. Designed to solve scalability challenges by automating repetitive, low-complexity questions that previously overwhelmed the human support team.

Multi-Agent Personal Assistant & Time Organizer

AI Engineer

Built a sophisticated personal productivity automation system based on a Multi-Agent Architecture to streamline tasks and professional collaboration. The system integrates with Google Workspace, Jira, Zoom, and Confluence to provide unified task management, automated scheduling, and intelligent email triage. A Supervisor Agent orchestrates specialized sub-agents that autonomously handle complex workflows like research and meeting coordination while maintaining human-in-the-loop security.

AI-Assisted Governance Agent for a Data Clean Room Platform

AI Engineer / Solution Architect

The project involved designing and productionizing an AI-assisted governance and code review system for a privacy-preserving Data Clean Room platform. The platform was built to support secure data collaboration across isolated client environments, where SQL, PySpark, Scala, and pipeline definitions had to comply with strict privacy, PII, data-contract, and governance rules. The AI assistant was designed to analyze engineering changes before execution, detect potential policy violations, explain risks, and provide actionable recommendations to engineers. Instead of using an unconstrained chatbot approach, the solution combined LLM reasoning with structured platform context, explicit governance rules, deterministic validation checks, and human-in-the-loop approval flows.

Cloud-Agnostic High-Load Advertising Platform with Bidder and Data Platform

Solution Architect / Lead Engineer

The project involved designing and building a cloud-agnostic buy-side advertising platform (Demand-Side Platform). The platform included high-load real-time bidding components, campaign and targeting management, event ingestion, data processing pipelines, and a reporting layer based on ClickHouse. The system was designed for programmatic advertising workloads where latency, throughput, cost efficiency, and data reliability are critical. The architecture supported real-time bid request processing, campaign targeting, audience and frequency-capping checks, event logging, aggregation, and business reporting. The infrastructure was built to run in a Kubernetes-based environment with Terraform-based provisioning, allowing deployment across different cloud providers or private infrastructure.

AI-Powered Loan Application Processing Platform

Solution Architect

Architected and developed a sophisticated loan application processing platform with agentic AI capabilities for a fintech lending company. The system combines an N8N-inspired declarative workflow engine with LLM-powered agents equipped with 30+ MCP tools for autonomous task execution. Core modules include automated bank statement extraction and fraud detection, vector-powered semantic search for document analysis, and multi-tenant architecture with complete data isolation across 76 database tables.

AI-Driven SDLC Transformation & Developer Productivity Platform

Staff Engineer

Led an AI-first transformation of the software development lifecycle for a charity and volunteering platform serving enterprise clients. The initiative encompassed driving AI code-generation adoption across the engineering team, building AI-powered internal tooling integrated into sprint workflows, implementing MCP servers for streamlined AI-assisted development, and constructing a RAG-powered knowledge base to surface institutional knowledge at scale. The project spanned full-cycle development including requirements, architecture, security, and policy integrations using an AI-first approach.

Smart IoT Cloud Platform

Lead Cloud Engineer

Led cloud-native development and a team of 5 engineers for a smart consumer IoT platform processing real-time device telemetry from connected smart beds. The platform managed cloud infrastructure for hundreds of thousands of connected devices, encompassing microservice architecture, real-time observability, data lifecycle management, and compliance reporting across AWS-native services.