Data Scientist and AI Engineer shipping GenAI + RAG, information extraction, and document translation platforms to production. Product Owner and Team Lead across roadmap, architecture, delivery, and quality for high-concurrency ML services. Hands-on with Python, FastAPI, LangChain, LLMs, vector DBs (Qdrant), OCR, and microservices; deploy with Docker, CI/CD, and cloud patterns (AWS/Azure). Built async services that cut p95 latency, scaled multimodal RAG (docs/images/video/audio), and automated ingestion pipelines that update vector stores with zero downtime. Recent work: production-grade information extraction for complex PDFs; passport/KYC with image enhancement, live face match, and anti-spoofing; GenAI chat with grounded answers, feedback scoring, and auto-regeneration; translation workflows with OCR for scanned/handwritten text and editor telemetry. What’s next: leading hybrid teams to ship reliable, observable ML systems—measurable lifts in accuracy/conversion, faster deployments, and lower infra cost through better retrieval, orchestration, and monitoring. Open to roles in Data Science, ML Engineering, and AI Product leadership. Keywords: RAG, LangChain, LLMs, FastAPI, Python, Qdrant, OCR, NLP, microservices, async, Docker, CI/CD, AWS, Azure, PostgreSQL, MongoDB, observability.
