About
I’m focused on NLP (RAG, embeddings, fine-tuning), ML in production, and operational efficiency.
What I do
- Build AI/NLP APIs with FastAPI, optimize latency & cost.
- Deploy with Docker/Kubernetes, CI/CD, monitoring (logs/metrics).
- Design data pipelines, model evaluation, A/B testing.
Strengths
Design solutions from data → models → deployment → operations. Priorities: stability, measurable quality, scalability.
Skills
Some areas I often work on and keep improving.
NLP / LLM
RAG, embeddings, vector DB, prompt engineering, evaluation, basic fine-tuning.
Backend
FastAPI, REST, auth, async, caching, testing, clean architecture.
DevOps
Docker, K8s, Nginx, CI/CD, observability, Linux hardening.
Repos I’m interested in
Pulled from GitHub (recent ⭐ / recent forks) and ranked by “goodness” (stars + forks + recency).
Featured repos
Manually pinned repos that represent my portfolio.
Contact
If you want to discuss a project, collaborate, or just connect.