Software Engineer at Technosec.io (4+ years), building production-grade AI systems with multi-agent orchestration, RAG pipelines, and scalable full-stack architectures. Open-source contributor to the JupyterLab ecosystem.
|
~15,000 LoC | 14 Autonomous Agents Production platform using LangGraph, LangChain, and FastAPI. Agents with real autonomy — accept, refuse, question, retry, and delegate via state-machine supervisor with intelligent LLM routing.
|
Semantic Search & Document Intelligence Full retrieval-augmented generation pipeline with document chunking, Ollama embeddings, vector storage, and semantic search across CSV, PDF, JSON, and Markdown.
|
|
Next.js 16 / React 19 Frontend WebSocket streaming, chat history, file upload for RAG, and agent status visualization with Zustand state management and Recharts.
|
200+ E2E Tests | 80%+ Coverage Selenium + Playwright across 3 browsers. Parallel CI/CD execution reducing QA cycle from 3 days to under 4 hours. Percy visual regression for 25+ flows.
|
|
Open-Source | 90%+ Adoption Custom TypeScript + React extensions reducing repetitive tasks by ~35% for 15+ data scientists. Contributed to JupyterLab 4.2.0.
|
Claude Code | MCP Servers Orchestrating specialized agents for code review, security analysis, and automated testing with custom MCP servers, hooks, and prompt engineering.
|
