AI Prompt Engineer / Agentic AI Engineer (Onsite/Hybrid)

We are seeking a hands-on AI Agent Engineer to design, develop, and deploy intelligent agents that can reason, use tools, and execute complex enterprise workflows. The ideal candidate will have practical experience building LLM applications and agentic systems, integrating enterprise tools and APIs, and implementing Retrieval-Augmented Generation (RAG) solutions.

This role emphasizes demonstrated engineering depth, practical implementation skills, and the ability to build, evaluate, secure, and maintain production-ready AI agents. No minimum years of experience are specified.

• Design, develop, and deploy LLM applications and agent workflows using frameworks such as Semantic Kernel, LangChain, LangGraph, AutoGen, CrewAI, or comparable technologies.

• Build and integrate Model Context Protocol (MCP) servers, tools, APIs, and enterprise connectivity solutions.

• Develop AI agent applications using Python, TypeScript, or similar programming languages.

• Implement prompt optimization, agent planning, memory, context management, and multi-step execution.

• Build RAG pipelines using embeddings, vector databases, and knowledge-grounding techniques.

• Integrate AI agents with platforms such as Azure AI Foundry, Azure OpenAI, AWS Bedrock, Google Vertex AI, or comparable services.

• Evaluate and test agent behavior, reliability, and performance.

• Deploy, monitor, troubleshoot, and maintain AI agent applications.

• Implement appropriate security, governance, and operational controls for enterprise AI systems.

• Support the development of enterprise copilots, AI assistants, and integrations with existing business systems.

• Demonstrated experience building LLM applications and agent workflows using an agent framework or comparable technology.

• Hands-on experience with MCP servers, tool integration, API orchestration, and enterprise connectivity.

• Programming experience in Python, TypeScript, or a similar language.

• Practical knowledge of prompt optimization, agent planning, memory, context management, and multi-step execution.

• Experience with RAG, embeddings, vector databases, and knowledge grounding.

• Familiarity with at least one AI platform, such as Azure AI Foundry, Azure OpenAI, AWS Bedrock, Google Vertex AI, or a comparable platform.

• Experience with agent evaluation, testing, deployment, monitoring, and troubleshooting.

• Understanding of AI application security and governance.

• Experience developing enterprise copilots and AI assistants.

• Experience integrating AI agents with healthcare systems or other regulated enterprise environments.