Skip to main content
Download free report
SoftBlues
Back to Directory
MZ

Mykhailo Z.

Voice AI Engineer

Voice AI Engineer
7+ yearsCET (GMT +1)

About

Mykhailo is an experienced AI Engineer with a deep specialization in Voice AI and real-time audio processing. His unique expertise bridges the gap between high-level LLM orchestration and low-level telephony engineering. He excels at building ultra-low-latency voice agents and resilient STT/TTS pipelines, where every stage, from codec selection to custom VAD logic is meticulously optimized for high performance in challenging environments. His track record ranges from developing secure, air-gapped transcription systems for law enforcement to launching financial AI assistants that maintain stability even over unstable mobile networks. Beyond voice technologies, Mykhailo designs sophisticated Agentic RAG systems and multimodal architectures using LangGraph, Neo4j, and modern Vision-Language models. He also masters the full MLOps lifecycle: from building distributed data processing systems on Ray.io and Kubernetes to high-load model serving via vLLM and Triton. His work is consistently driven by a steadfast focus on data security and operational efficiency.

Key Expertise

Voice AI AgentsReal-time Audio StreamingAgentic RAG SystemsOn-premise LLM DeploymentSpeech EngineeringMultimodal Document AI

Interested in Mykhailo?

Tell us about your project and we'll confirm availability within 24 hours.

No commitment required
7-day risk-free trial
Response within 24 hours

Project Portfolio

2024

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.

View Details
2025

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.

View Details
2025

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).

View Details
2023-2024

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.

View Details
MZ

Ready to Work with Mykhailo Z.?

Voice AI Engineer

Share your project details and our team will review the match and confirm availability.

Browse More Experts

No commitment required. We respond within 24 hours.