Huang Kevin

👋 Hey, I’m Kevin Huang, an AI Developer / Machine Learning Engineer (GenAI + MLOps) based in Canada, building production-ready LLM applications that turn messy, unstructured data into useful answers and real business outcomes.

I’ve worked across enterprise and finance, where I’ve helped teams move from “cool prototype” to reliable, monitored, API-driven GenAI systems.

What I do best:

✅ Build and productionize RAG pipelines (LangChain, embeddings, vector search)

✅ Ship FastAPI microservices with performance, caching, retries, and stability in mind

✅ Design LLM evaluation + QA workflows (rubrics, test cases, failure modes, iteration loops)

✅ Deploy with Docker + CI/CD, and support observability/monitoring for real usage

✅ Collaborate closely with product, research, and engineering to turn experiments into features

My toolkit includes:

Python, FastAPI, LangChain, PostgreSQL/pgvector, Pinecone, vector DBs, cloud (AWS/GCP), CI/CD, monitoring/observability, and responsible AI basics.

If you’re building GenAI products and need someone who can prototype fast and make it production-safe, feel free to reach out.