AI Backend Engineer focused on building production-grade LLM applications, agentic workflows, RAG systems, and scalable Python APIs.
I work across the full AI product stack: from backend architecture and API design to LLM orchestration, vector search, cloud deployment, observability, and automation.
- Agentic AI systems using OpenAI Agents, LangGraph, LangChain, MCP, and tool-calling workflows
- RAG applications with vector databases, structured retrieval, source attribution, and domain-specific prompts
- Scalable Python backends using FastAPI, Django, Celery, Redis, PostgreSQL, and WebSockets
- Cloud-native AI services on AWS, Azure, GCP, Firebase, Docker, Kubernetes, and serverless platforms
- Healthcare, HR, support, transcription, analytics, and automation platforms powered by LLMs
- Production LLM systems
- Multi-agent AI workflows
- Healthcare AI automation
- RAG evaluation and retrieval quality
- Scalable backend architecture
