Job Summary
We are seeking a skilled AI Engineer with strong expertise in Generative AI, enterprise-grade Generative AI applications Prompt Engineering, Retrieval-Augmented Generation (RAG), LangGraph, Elastic Knowledge, and Python. You will build intelligent AI agents, optimize RAG pipelines, and integrate knowledge bases to deliver scalable AI solutions for business needs.
Responsibilities
- Design and develop enterprise Generative AI applications using Python to meet business requirements
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines to enhance knowledge retrieval accuracy
- Develop AI workflows and multi-agent systems leveraging LangGraph to orchestrate complex tasks
- 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 for efficient search
- Develop intelligent AI assistants, chatbots, and agentic AI solutions to improve user engagement
- Connect LLMs with enterprise APIs, databases, and document repositories to enable seamless data access
- Optimize retrieval quality, context management, and response accuracy to enhance AI performance
- Implement vector search and semantic search capabilities using vector databases such as Pinecone, Chroma, FAISS, Weaviate, or Milvus
- Evaluate, fine-tune, and monitor LLM performance to ensure reliability and effectiveness
- Collaborate with business stakeholders to translate AI use cases into technical solutions that drive value
- Follow AI governance, security, and responsible AI best practices to maintain compliance and ethical standards
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
- Strong knowledge of Retrieval-Augmented Generation (RAG) techniques for knowledge retrieval
- Experience with 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
- Experience with 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 semantic search
- Experience building AI agents and multi-step workflows to automate complex processes
- Strong understanding of REST APIs and microservices for system integration
- Familiarity with Git, Docker, and CI/CD pipelines for version control and deployment automation
