Design, build, and deploy production-grade AI/LLM systems and agentic workflows. Implement prompt and context engineering, RAG, vector search, and LangGraph-based agents. Develop backend APIs, data pipelines, and monitoring for performance, scalability, and cost optimization while collaborating with product, data science, and engineering teams.

Develop, integrate, and support AI/LLM-powered applications and agent workflows. Assist with prompt engineering, context management (RAG/vector search), Python-based APIs and data pipelines, testing, monitoring, and collaboration with product and data teams under senior supervision.

Lead architecture, build, and deploy context-rich LLM and agent-based AI solutions. Design prompts, manage context/RAG and vector search, implement production Python services, integrate models and agents, ensure data pipeline quality, monitor and optimize agent performance, and guide cross-functional teams on scalable, secure AI deployments.