AI Full-Stack Engineer • LLM Apps • RAG Systems • Scalable APIs • Modern Web
- LLM-powered products: assistants, agents, tool-use workflows, evals, safety/guardrails
- RAG / Search: embeddings, hybrid retrieval, re-ranking, chunking strategies, observability
- Full-stack delivery: fast APIs, clean UI, auth/payments, deployments, monitoring
- Data & MLOps: training/inference pipelines, model serving, experiment tracking
AI / ML
- Python, PyTorch, Transformers, LangChain/LlamaIndex
- Vector DBs: Pinecone / Weaviate / FAISS (pick what you use)
- Evaluation: prompt evals, regression tests, offline/online metrics
Backend
- FastAPI / Django, Node.js, REST/GraphQL
- Postgres, Redis, Kafka (optional)
- Auth: OAuth/JWT, RBAC
Frontend
- TypeScript, React / Next.js
- TailwindCSS, component systems, data viz
Infra / MLOps
- Docker, Kubernetes (optional), GitHub Actions
- AWS/GCP/Azure (choose), Terraform (optional)
- Observability: OpenTelemetry, Grafana/Prometheus (optional)
If you’re building LLM apps, RAG/search, or AI product UX, I’m happy to collaborate.





