Technical AI Lead

Design, build, and optimize agentic systems and multi-agent workflows for real-world use cases Develop and maintain tailored LLM pipelines using frameworks such as LangChain, LangGraph, and related ecosystems Deploy, serve, and optimize open-source LLMs using vLLM, TGI (Text Generation Inference), and Python-based inference stacks Work extensively with open models such as Qwen, Llama, Mistral, and other leading model families, including fine-tuning, evaluation, and integration Implement scalable AI services with robust prompt engineering, autonomous task planning, and tool execution Define AI architecture, performance benchmarks, and best practices in collaboration with cross-functional teams Provide technical leadership, mentor team members, and ensure high engineering standards across deliverables Required Skills & Experience 6+ years of strong hands-on experience in Python development Proven expertise in Agentic AI, agent frameworks, and autonomous orchestration systems Hands-on experience building custom LLM pipelines and multi-agent systems Solid experience with vLLM, TGI, and model serving infrastructure Extensive exposure to open-source LLMs such as Qwen, Llama, Mistral, and similar models Strong working knowledge of LangChain, LangGraph, and related agent frameworks Deep understanding of inference optimization, embeddings, vector databases, and model integration patterns Excellent communication skills with the ability to clearly articulate ideas to leadership and peers Strong delegation, influence, and decision-making capabilities Preferred / Nice-to-Have Skills Experience designing multi-agent architectures for analytics, automation, or workflow systems Ability to build custom tools, connectors, or model-controller interfaces (e g , MCP) Hands-on experience with RAG pipelines, LLM evaluation frameworks, and scalable inference environments Prior experience leading or owning AI platforms or agent-based systems end-to-end