Oleksandr N.

Project overview:

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.

Responsibilities:

• Architected scalable agent deployment workflows to manage complex state-based transitions and multi-agent handoffs.
• Developed a robust CI/CD pipeline using Terraform and Helm to automate the provisioning of agent environments on Kubernetes clusters.
• Implemented a unified API gateway using FastAPI to standardize agents deployment.

Achievements:

Accelerated Time-to-Market: Delivered the MVP from concept to launch in just 2 months, resulting in the immediate acquisition of 10 initial B2B clients. Enhanced Observability: Built a comprehensive monitoring suite that tracks agentic reasoning paths, ensuring high-fidelity output and debugging capabilities.

Technology stack:

Project overview:

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.

Responsibilities:

• Architected the solution, built an engineering team from the ground up, personally developing the platform’s foundational infrastructure while directing overall product execution.

Achievements:

Implemented an end-to-end AI mobile application, successfully acquiring 60k+ downloads and 8k monthly active users (MAU).

Technology stack:

Project overview:

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.

Responsibilities:

• Directed two cross-functional teams (10+ engineers and architects) through the full SDLC, from initial discovery to production-grade deployment.
• Designed a modular ingestion architecture using Airflow to handle complex document partitioning, embedding generation, and metadata enrichment.
• Defined the technical roadmap and infrastructure standards, including the transition to a hybrid search approach (Elasticsearch + Vector embeddings).

Achievements:

Engineered a high-throughput data pipeline capable of processing diverse file formats with sub-second retrieval latency for inference. Successfully onboarded two enterprise clients, centralizing their fragmented internal knowledge management into a unified AI interface.

Technology stack:

Project overview:

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.

Responsibilities:

• Developed automated ETL workflows in n8n to synchronize cloud storage with Pinecone vector embeddings.
• Configured semantic search parameters to optimize retrieval accuracy for technical and legal documentation.
• Implemented a natural language interface allowing non-technical users to extract complex data from PDFs and spreadsheets.

Achievements:

Rapid Internal Adoption: Successfully deployed a functional knowledge management tool within one week, immediately streamlining internal documentation workflows. Eliminated Manual Indexing: Automated the entire document lifecycle, reducing the time from "file upload" to "queryable insight" to under 60 seconds.

Technology stack: