Datadog's MCP team is scaling the capabilities of our MCP Services — an interface that enables external agents like Claude and Cursor, as well as internal Datadog AI Agents, to interact with Datadog data. As a Staff Engineer, you'll play a critical role in evolving this agent-friendly tool surface, enabling agentic workflows across metrics, logs, and incidents etc. You'll drive forward advanced evaluation frameworks for agentic systems and contribute to the next generation of agent-tool interaction models. This is a fast-evolving space with deep ambiguity and high impact — ideal for someone eager to help shape Datadog's applied AI future.
At Datadog, we place value in our office culture - the relationships and collaboration it builds and the creativity it brings to the table. We operate as a hybrid workplace to ensure our Datadogs can create a work-life harmony that best fits them.
What You'll Do:
* Lead efforts to improve Datadog's public-facing MCP server, enabling intelligent agents to discover and interact with our services
* Design and implement agentic tool surfaces tailored for evaluation and production use across a wide variety of AI agents
* Build and maintain advanced evaluation pipelines for measuring agent performance on Datadog workflows (e.g., investigations, incident triage, metric queries)
* Investigate and resolve failure cases by analyzing tool output, improving query parsing, and enhancing agent feedback mechanisms
* Collaborate across Applied AI and internal teams to align on shared standards for tool integration and data access
Who You Are:
* Experienced Staff-level engineer with a strong background in applied AI, agentic programming, and/or the following: LLM-powered automation pipelines, LLM orchestration frameworks (e.g., LangChain, LangGraph, CrewAI), Agent orchestration and tool-use systems
* Comfortable working in high ambiguity and fast-changing environments; able to define and prioritize direction autonomously
* Skilled in building evaluation frameworks for LLM agents or AI systems, including metrics design and data instrumentation
* Bonus: Experience working with the MCP standard or contributing to agent-compatible tooling surfaces, familiarity with building and evaluating ReAct agentic loops
* Strong systems thinking, able to reason across multiple agents, tools, and user scenarios
* Passionate about pushing boundaries in agent-augmented software and eager to shape evolving interfaces
Datadog values people from all walks of life. We understand not everyone will meet all the above qualifications on day one. That's okay. If you're passionate about technology and want to grow your skills, we encourage you to apply.
Benefits and Growth:
* Generous and competitive benefits package
* New hire stock equity (RSUs) and employee stock purchase plan
* Continuous career development and pathing opportunities
* Employee-focused best in class onboarding
* Internal mentor and cross-departmental buddy program
* Friendly and inclusive workplace culture
Benefits and Growth listed above may vary based on the country of your employment and the nature of your employment with Datadog.