AI Engineer (GenAI / RAG / LangGraph / Python)

Description We are looking for a highly skilled AI Engineer with strong expertise in Generative AI, Prompt Engineering, Retrieval-Augmented Generation (RAG), LangGraph, Elastic Knowledge, and Python . The ideal candidate should have experience designing, developing, and deploying enterprise-grade AI applications powered by Large Language Models (LLMs) and modern AI frameworks.

The candidate should be capable of building intelligent AI agents, orchestrating complex workflows using LangGraph, integrating enterprise knowledge bases, and developing scalable GenAI solutions for business use cases.

Key Responsibilities

Design and develop enterprise Generative AI applications using Python. Build and optimize Retrieval-Augmented Generation (RAG) pipelines for knowledge retrieval. Develop AI workflows and multi-agent systems using LangGraph. Create effective prompts and prompt templates for various LLM use cases. Integrate enterprise knowledge repositories using Elastic Knowledge or Elasticsearch-based knowledge systems.

Develop intelligent AI assistants, chatbots, and agentic AI solutions. Connect LLMs with enterprise APIs, databases, and document repositories. Optimize retrieval quality, context management, and response accuracy. Implement vector search and semantic search capabilities. Evaluate, fine-tune, and monitor LLM performance.

Collaborate with business stakeholders to understand AI use cases and translate them into technical solutions. Follow AI governance, security, and responsible AI best practices.

Required Skills

Strong Python programming experience. Hands-on experience with LangGraph . Strong knowledge of Retrieval-Augmented Generation (RAG) . Experience with Prompt Engineering and prompt optimization. Experience developing applications using Generative AI technologies. Knowledge of Elastic Knowledge / Elasticsearch for enterprise search and knowledge retrieval.

Experience with LangChain ecosystem. Experience integrating OpenAI, Azure OpenAI, Anthropic Claude, Gemini, or similar LLMs. Knowledge of vector databases such as Pinecone, Chroma, FAISS, Weaviate, or Milvus. Experience building AI agents and multi-step workflows. Strong understanding of REST APIs and microservices. Familiarity with Git, Docker, and CI/CD pipelines.