I bridge the gap between complex AI research and production-grade engineering. With over 7 years of experience, I specialize in building scalable FastAPI microservices, asynchronous data pipelines, and advanced Agentic AI/RAG workflows that handle enterprise-scale workloads.
- Languages & Core: Python (Asyncio, OOP), SQL, Bash, Rust (Extensions)
- AI & Generative AI: RAG Pipelines, Multi-Agent Orchestration (LangGraph, LlamaIndex), Semantic Search, LLM Evaluation (Langfuse)
- Backend & Microservices: FastAPI, Flask, Distributed Task Queues (Taskiq, Celery), Event-Driven Architecture
- Databases & Vector Infra: PostgreSQL, Redis, Qdrant, Pinecone, FAISS
- DevOps & MLOps: Docker, Kubernetes, AWS (EC2, S3, Lambda, EKS), GitHub Actions CI/CD
- Engineering ultra-low latency inference gateways for multi-LLM routing.
- Designing stateful, multi-agent automation workflows using advanced graph architectures.
- Optimizing background data-ingestion pipelines for multi-million document vector embedding.
📬 Let's Connect: [email protected] | San Francisco, CA