Description

You will lead the development of generative AI solutions, including multi-agent workflows and RAG pipelines. This role is on-site.

Responsibilities

• Build multi-step and multi-agent workflows using LangChain and LangGraph.
• Implement Retrieval Augmented Generation (RAG) pipelines and document retrieval strategies.
• Design prompt templates, system instructions, and guardrails to mitigate hallucinations.
• Integrate agents with tools, APIs, and internal services.
• Optimize latency, accuracy, and token usage across LLM implementations.

Required Skills

• 7+ years of professional software development experience.
• Strong Python development skills.
• Hands-on experience with LLMs, embeddings, and prompt engineering.
• Proficiency with LangChain, LangGraph, and other agent/RAG frameworks.
• Experience utilizing LLM APIs (Gemini, Bedrock, Vertex AI, Claude).
• Experience with vector databases like Pinecone or Weaviate.
• Understanding of hallucination mitigation techniques.
• Familiarity with cloud AI services.

Key Skills

Education

Any Graduate