• Build and optimize agentic systems and multi-agent workflows for real-world applications. • Develop tailored LLM pipelines using frameworks such as LangChain, LangGraph, and related ecosystems. • Deploy and optimize open-source LLMs using vLLM, TGI (Text Generation Inference), and Python-based inference stacks. • Work with diverse open models (Qwen, Llama, Mistral, etc.) including fine-tuning, evaluation, and integration. • Implement scalable AI services with robust prompt engineering, autonomous task planning, and tool execution. • Collaborate with cross-functional teams to define architecture, performance goals, and best practices.