AI Engineer (Genai / Rag / Langgraph / Python)

Job Summary We are seeking a skilled AI Engineer to design, develop, and deploy enterprise-grade Generative AI applications using Python and modern AI frameworks. You will build intelligent AI agents, optimize RAG pipelines, and integrate enterprise knowledge bases to deliver scalable AI solutions. Responsibilities Design and develop enterprise Generative AI applications using Python to meet business needs Build and optimize Retrieval-Augmented Generation (RAG) pipelines for accurate knowledge retrieval Develop AI workflows and multi-agent systems using LangGraph to orchestrate complex processes Create and refine prompts and prompt templates for diverse Large Language Model (LLM) use cases Integrate enterprise knowledge repositories using Elastic Knowledge or Elasticsearch-based systems Develop intelligent AI assistants, chatbots, and agentic AI solutions to enhance user interaction Connect LLMs with enterprise APIs, databases, and document repositories for seamless data access Optimize retrieval quality, context management, and response accuracy in AI applications Implement vector search and semantic search capabilities using vector databases Evaluate, fine-tune, and monitor LLM performance to ensure reliability and effectiveness Collaborate with business stakeholders to translate AI use cases into technical solutions Adhere to AI governance, security, and responsible AI best practices in all developments Required competencies and certifications Strong Python programming experience for AI application development Hands-on experience with LangGraph for building AI workflows and multi-agent systems In-depth knowledge of Retrieval-Augmented Generation (RAG) techniques Expertise in Prompt Engineering and prompt optimization for LLMs Experience developing applications using Generative AI technologies Knowledge of Elastic Knowledge or Elasticsearch for enterprise search and knowledge retrieval Familiarity with the LangChain ecosystem for AI development Experience integrating OpenAI, Azure OpenAI, Anthropic Claude, Gemini, or similar LLMs Knowledge of vector databases such as Pinecone, Chroma, FAISS, Weaviate, or Milvus for vector search Experience building AI agents and multi-step workflows to automate tasks Strong understanding of REST APIs and microservices for system integration Familiarity with Git, Docker, and CI/CD pipelines for version control and deployment automation