We are seeking a highly skilled lead engineer with deep expertise in Agentic AI, autonomous agents, and Large Language Models (LLMs). The ideal candidate has 6+ years of hands-on experience in Python and open-source model ecosystems, with proven ability to design and deploy tailored AI pipelines and work with a wide range of open models (e.g., Qwen, Llama, Mistral, and others).

Shift timing : 5PM to 1AM

Responsibilities :

- 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.

Required Experience :

- Strong proficiency in Python

- Expertise in Agentic AI, agent frameworks, and autonomous orchestration.

- Hands-on experience with tailored pipelines for LLMs and multi-agent systems.

- Experience with vLLM, TGI, and model serving infrastructure.

- Extensive work with open-source LLMs (Qwen, Llama, Mistral, and similar families).

- Experience with LangChain, LangGraph, and related agent frameworks.

- Solid understanding of inference optimization, embeddings, vector search, and model integration patterns.

- Clear Communication Effectively communicates with leadership and peers.

- Delegation Skills Able to delegate work efficiently and responsibly.

- Influence & Persuasion : Capable of influencing management and peers toward effective solutions.

Preferred Experience :

- Multi-agent architectures for analytics, automation, or workflow systems.

- Building custom tools, connectors, or model-controller interfaces (e.g., MCP).

- Experience with RAG pipelines, evaluation frameworks, and scalable inference environments.