I build the whole path — fine-tuning and RAG pipelines through inference APIs, AWS deployment, and live evaluation. Three systems in production across financial news and genomics.
LoRA / PEFT fine-tuning, dataset curation, mixed-precision training on A100
Hybrid vector + BM25 fusion, cross-encoder reranking, HyDE, semantic caching
FastAPI async services, GPU endpoints, auth, rate limiting, OpenAPI contracts
AWS EKS and serverless Lambda, Docker, CloudFront, GitHub Actions CI/CD
Circuit breakers, exponential backoff, multi-provider failover, graceful degradation
Precision@K, MRR, NDCG, LLM-as-judge faithfulness scoring, CI quality gates
Retrieval-augmented chat over 138 market news articles across 7 tickers, answering natural-language questions with AI summaries grounded in cited sources. Built to production standards: every answer traces back to a source, is measured for faithfulness, and is served behind a circuit breaker that degrades gracefully instead of erroring.
An end-to-end vertical slice of LLM productization: fine-tune a base model on a curated domain corpus, serve it behind a hardened inference API, and ship a streaming chat client — deployed on Kubernetes with automated rollout. The corpus here is genetics; the pipeline is domain-agnostic.
Image annotation tool for creating high-quality labeled datasets for machine learning models — polygon annotations, time-lapse comparison with auto-detection, and multiple export formats. Domain-independent by design; the bundled demo set happens to be histopathology slides.