To design and build intelligent, agent-based systems leveraging Model Context Protocol (MCP) and advanced LLM frameworks. This role focuses on developing autonomous AI agents capable of tool use, memory management, multi-step reasoning, and system orchestration across enterprise environments.
The ideal candidate will architect scalable agentic workflows, integrate APIs and data sources via MCP standards, implement context-aware memory systems, and ensure safe, reliable AI execution. Responsibilities include prompt engineering, tool integration, evaluation frameworks, guardrail implementation, and performance optimization.
Strong experience with LLM ecosystems (e.g., OpenAI APIs), multi-agent architectures, retrieval-augmented generation (RAG), and production-grade deployment is required. Familiarity with AI safety, monitoring, and human-in-the-loop systems is highly preferred.