# Bohdan Fesenko

Bohdan Fesenko is an engineer in Kyiv who builds systems where AI agents and people do real work together. He led engineering at a pre-MVP consumer startup, took a five-person team from no process to a shipped product, and made agent-assisted development a reviewable practice. He now builds agent platforms and measured detection-and-tracking pipelines.

## Experience

### Engineering Lead - Pre-MVP consumer family app (stealth), COPPA-regulated

Nov 2025 - Sep 2026

- Directly responsible for all engineering. Took a five-person team from no engineering process to a core loop live on TestFlight in about three months, then worked as platform architect and informal lead of the Ukrainian team.
- 148 merged pull requests across a seven-app monorepo in ten months; 95 database migrations, 452 test files and 29 CI workflows touched; about a third of the code volume while leading.
- Designed and shipped the product's entire MCP surface: an SSE resource substrate with a change-detection event bus, five live resources, an 83-tool catalog with per-tool annotations and boot-time registry validation, and OAuth with dynamic client registration for third-party MCP clients.
- Introduced agentic development on day one, then made it reviewable: an AI-coding course as onboarding gate, review of AI sessions as part of code review, a scored rubric with named red flags, an agent-orchestration work tracker, and a multi-model adversarial review tool.
- Wrote the team's planning and review protocol: goals not tasks, adversarial reviewers so knowledge spreads, approvals scaled to change size, review SLAs from four hours to thirty minutes for hotfixes.

Stack: TypeScript, Node.js, Fastify, MCP, Mastra, PostgreSQL, Drizzle, Supabase, React Native, Expo, Next.js, Cloud Run, GitHub Actions, Gemini / Vertex AI, Claude Code, BMAD

### AI engineer, agents and LLM applications - AI agents marketplace

Jan 2025 - Jul 2025

- Built the agent backend and proof-of-concept agents for an AI agents marketplace, with a testing UI for evaluating agent behaviour before release.
- Shipped an LLM chat front end adapted to the marketplace's agents, and the demo the product was presented with.

Stack: Python, LLM agents, agent evaluation, TypeScript, Next.js

### Founder and AI lead - Own AI product venture

Sep 2023 - Dec 2024

- Built generative-AI products with search and retrieval, agent workflows and custom tools.
- LLM applications for clients, including an ad-recommendation MVP with keyword analysis and several product front ends; a public Kaggle ship-detection solution.

Stack: Python, TypeScript, RAG, LLM agents, FastAPI, Next.js

### AI engineer - Freelance client work

Nov 2021 - Sep 2023

- Delivered more than 20 generative-AI projects for clients, from NLP chatbots to AI workflow automation.

Stack: Python, LLM applications, NLP, chatbots, workflow automation

### Lead Machine Learning Engineer - ML services team, enterprise clients

Nov 2020 - Nov 2021

- Led a team of three engineers: hiring, training and growth.
- Designed end-to-end ML solutions for enterprise clients, aimed at cost savings and process automation.

Stack: Python, machine learning, MLOps, team lead

### Machine Learning Engineer - Adaptive e-learning platform

Jul 2019 - Nov 2020

- Built the machine learning pipelines behind personalised courses; course completion rose 23%.
- Built NLP answer-matching models that enabled new course features; bad reviews fell 37%.

Stack: Python, NLP, ML pipelines, recommendations

### Data Scientist - Computer vision company

Nov 2018 - Jul 2019

- Built a face recognition system: a new network architecture, dataset and training method for image-quality estimation and embedding aggregation.
- Shipped the full pipeline as six neural networks on one server, serving four real-time Full HD streams on a single GTX 1080 Ti; deployed in several Ukrainian cities.

Stack: Python, deep learning, face recognition, real-time video, GPU inference

## Skills

### Languages

- TypeScript
- Node.js
- Python
- C++17
- SQL
- Rust

### ML and numerics

- vectorised numpy and scipy
- Kalman and IMM
- GNN and JPDA
- SPRT and M-of-N
- track-before-detect
- Cramér-Rao bounds
- MOTA / IDF1 / HOTA
- LLM routing and evaluation

### Systems

- Fastify
- PostgreSQL and Drizzle
- Supabase
- SSE and WebSocket
- OAuth 2.0 and DCR
- Google Cloud Run
- GitHub Actions
- testcontainers
- React Native and Expo
- Next.js
- real-time on ARM edge

### Agents and LLM tooling

- Model Context Protocol, server side
- Mastra
- Claude Code, Codex, Cursor, BMAD
- Agent Client Protocol
- multi-model adversarial review
- agent-orchestration trackers

### Leadership

- team of five as Engineering Lead
- planning and review protocols
- sprint artifacts with capacity and dependencies
- onboarding engineers onto agentic development
