Key Responsibilities

• Design and develop scalable Generative AI backend applications
• Build and maintain Retrieval-Augmented Generation (RAG) pipelines
• Integrate and deploy Large Language Models (OpenAI, Azure OpenAI, Anthropic, or open-source LLMs)
• Develop REST APIs using FastAPI
• Work with vector databases such as Pinecone, FAISS, ChromaDB, or Milvus
• Apply prompt engineering, embeddings, and semantic search techniques
• Collaborate using Git, Docker, and cloud platforms (AWS, Azure, or GCP)
• Contribute directly to coding and implementation of production-grade AI solutions

Requirements

• 6+ years of experience in backend software development
• Strong proficiency in Python
• Hands-on experience with Retrieval-Augmented Generation (RAG)
• Strong experience with LangChain
• Expertise in FastAPI and REST API development
• Experience integrating and deploying Large Language Models (OpenAI, Azure OpenAI, Anthropic, or open-source LLMs)
• Knowledge of vector databases such as Pinecone, FAISS, ChromaDB, or Milvus
• Familiarity with prompt engineering, embeddings, and semantic search
• Experience with Git, Docker, and cloud platforms (AWS, Azure, or GCP)
• Experience with AI agents and multi-agent frameworks (preferred)
• Knowledge of MLOps and model deployment (preferred)
• Experience with CI/CD pipelines and containerized deployments (preferred)
• Exposure to Kubernetes (plus)
• Immediate joiner or short notice preferred
• Indian resident only; candidates from Andhra Pradesh and Telangana are not eligible

Skills Required