Job Summary
We are looking for a Software Engineer with strong experience in Generative AI and modern Python-based development. The ideal candidate will design and build advanced AI-driven systems, including LLM-based applications, agent workflows, and scalable backend services.
Key Responsibilities
Design and develop Generative AI applications using Python and LangChain
Build and orchestrate stateful AI workflows and multi-agent systems using LangGraph
Develop and deploy LLM-based solutions (OpenAI, Azure OpenAI, Claude, etc.)
Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases
Integrate AI services with enterprise systems, APIs, and data platforms
Develop backend services and APIs using FastAPI / Flask
Optimize AI workflows for performance, scalability, and reliability
Apply prompt engineering and agent orchestration patterns
Collaborate with cross-functional teams on delivery and integration
Ensure best practices in testing, monitoring, deployment, and production readiness
Required Skills
Strong programming experience in Python (3.x)
Hands-on experience with:
LangChain
LangGraph
Experience working with Large Language Models (LLMs) and Generative AI
Experience with RAG pipelines and vector databases (Pinecone, FAISS, Weaviate)
Experience building and consuming REST APIs
Familiarity with cloud platforms (AWS, Azure, or GCP)
Strong backend experience with FastAPI
Solid frontend experience using React.js (hooks, state management)
Experience Requirements
68 years of overall software engineering / AI/ML experience
Minimum 23 years of hands-on experience in AI / LLM-based application development