Gen AI Developer (Exp-4+ Years)-Full time-Hybrid

We are looking for an experienced GenAI Developer with strong hands-on experience in building and deploying Generative AI and LLM-powered applications. The ideal candidate should have expertise in Python, RAG, prompt engineering, AI agents, LangChain/LangGraph, vector databases, and cloud-based AI services.

Comparable current roles emphasize production-grade GenAI development with Python, LLMs, RAG, vector search, agentic workflows, FastAPI, and cloud deployment.

Key Responsibilities

• Design and develop enterprise-grade Generative AI applications.
• Build applications using Large Language Models (LLMs) such as OpenAI, Claude, Gemini, Llama, or other foundation models.
• Develop and implement RAG (Retrieval-Augmented Generation) solutions.
• Build document ingestion and processing pipelines, including chunking, embeddings, retrieval, and response generation.
• Design and optimize prompts for different business use cases.
• Develop AI agents and Agentic AI workflows.
• Implement multi-agent systems, tool calling, function calling, and workflow orchestration.
• Work with frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, or AutoGen.
• Integrate LLMs with enterprise applications, databases, APIs, and external tools.
• Develop scalable backend services using Python and FastAPI.
• Work with vector databases for semantic search and knowledge retrieval.
• Evaluate and improve LLM response quality, accuracy, latency, reliability, and cost.
• Implement AI security, guardrails, validation, and responsible AI practices.
• Deploy and support GenAI applications in production environments.
• Collaborate with Data Engineers, ML Engineers, Software Developers, Architects, and Product teams.

Required Skills

• 3+ years of experience in software development, with hands-on GenAI/AI experience.
• Strong proficiency in Python.
• Hands-on experience with Generative AI and LLM applications.
• Strong knowledge of Prompt Engineering.
• Experience designing and developing RAG pipelines.
• Experience with LangChain and/or LlamaIndex.
• Experience with LangGraph or Agentic AI frameworks is highly preferred.
• Experience with:
  • Embeddings
  • Semantic Search
  • Vector Search
  • Document Processing
  • Knowledge Retrieval
• Experience with vector databases such as:
  • Pinecone
  • FAISS
  • Chroma
  • Weaviate
  • PostgreSQL with pgvector
  • OpenSearch