• Build and scale AI agent workflows using Python, LangGraph, LangChain, and CrewAI, with a focus on scalable agentic architectures..
• Design and maintain data, memory, and RAG layers using PostgreSQL, SQLAlchemy/Alembic, vector databases (Qdrant/pgvector), embeddings, and chunking..
• Develop LLM-powered applications and multi-agent workflows, including tool/function calling, orchestration, routing, and state management..
• Integrate enterprise platforms and data sources including Snowflake and Salesforce to support AI-driven business workflows..
• Build reliable FastAPI services with Pydantic, PyTest, Docker, and automated testing for production AI applications..
• Implement LLM evaluation, observability, guardrails, and prompt-injection protection to improve AI reliability, quality, and security..
• Deploy, scale, and operate AI/LLM services on GCP, including cloud-native and production deployment practices..
• Use GitHub/GitHub Actions for source control, CI/CD, code reviews, and automated deployment workflows..
• Tech Stack: Python 3.11+, Pydantic v2, PostgreSQL, SQLAlchemy/Alembic, LangGraph, LangChain, CrewAI, LLM Agents, RAG, Qdrant/pgvector, embeddings, FastAPI, PyTest, Docker, GCP, Snowflake, GitHub..
• Good to Have: Salesforce, Gong, Glean..