Description

You will lead the development of LLM-powered applications, focusing on agentic AI workflows and RAG pipelines.

This role is on-site.

Responsibilities

• Develop agentic AI workflows and orchestration layers using LangChain and LangGraph.
• Implement Retrieval-Augmented Generation (RAG) pipelines with vector databases for grounded, accurate responses.
• Build and maintain backend services exposing LLM capabilities via FastAPI or Flask APIs.
• Deploy, monitor, and optimize AI services on AWS to ensure scalability and reliability.
• Integrate and manage vector stores such as Pinecone, ChromaDB, FAISS, or Weaviate for semantic search.

Required Skills

• 6-8 years of experience in AI/ML and LLM application development.
• Strong proficiency in Python for building LLM/AI services and data processing pipelines.
• Hands-on experience with LangChain and LangGraph for orchestrating LLM chains and agent workflows.
• Experience building production APIs using FastAPI or Flask.
• Deep understanding of AI/ML and generative AI concepts.
• Practical experience integrating RAG/LLM systems with vector databases.

Preferred Skills

• AWS cloud experience for deployment and operations of AI services.

Key Skills

Education

Any Graduate