GenAI & Agentic AI Engineer
persistent
Job Description
- Lead the design and development of enterprise AI applications powered by LLMs and Generative AI technologies.
- Build and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, including ingestion, chunking, embedding, indexing, retrieval, and response generation.
- Design and optimize retrieval strategies using semantic search, contextual awareness, and relevance ranking techniques.
- Develop and maintain MCP (Model Context Protocol) connectors that expose enterprise applications and APIs as agent-callable tools.
- Implement Agentic AI workflows capable of planning, reasoning, decision-making, and autonomous task execution.
- Contribute to AI orchestration frameworks that integrate RAG systems, MCP tools, workflow engines, and enterprise platforms.
- Develop scalable AI services and backend systems supporting production-grade AI solutions.
- Collaborate with architects, AI engineers, data engineers, and business stakeholders to convert business requirements into technical implementations.
- Drive prompt engineering, model tuning, evaluation, and AI optimization initiatives.
- Build proof-of-concepts, accelerators, and reusable AI components.
- Ensure security, governance, compliance, observability, and monitoring are integrated into AI applications.
- Support deployment and operation of AI workloads in containerized and cloud-native environments.
- Conduct technical reviews and establish AI engineering best practices.
- Mentor engineering teams and provide technical leadership on AI and data engineering initiatives.
- Stay updated with advancements in LLMs, Agentic AI, MCP, RAG architectures, and enterprise AI technologies.