Job Description
key Responsibilities :
Lead and mentor a team of LLM engineers and AI developers.
Architect and oversee the development of agent-based systems using LangGraph, LangChain, AutoGen, or similar frameworks.
Guide the design and deployment of scalable, production-grade LLM applications.
Ensure best practices for fine-tuning, prompt engineering, and hybrid LLM usage.
Oversee deployment on AWS / Azure with high performance and fault tolerance.
Collaborate cross-functionally with product managers, data scientists, and DevOps.
Requirements :
Deep knowledge of agent orchestration, task decomposition, and memory / tool usage in LLM workflows.
Proven experience in fine-tuning LLMs with CUDA-based optimizations.
Strong backend skills with FastAPI, Docker, and cloud deployment (AWS EC2, Lambda, AKS, etc.).
Track record of delivering LLM applications into production environments.
Experience with databases like MongoDB, PostgreSQL, or MySQL.
Hands-on experience with at least one cloud platform : AWS, Azure, or GCP.
Nice to Have :
Experience integrating async workflows (Celery, Ray) and event-driven architectures.
Familiarity with LangServe, Haystack, and vector store orchestration.
Open-source contributions or publications in LLM agent systems.
Experience leading code reviews, architectural discussions, and sprint planning.
Soft Skills :
Working Hours :
General Shift : 1 : 30 PM to 11 : 30 PM IST
Flexibility to extend hours based on critical deployments or support needs.
Manager • noida, India