Senior ML Performance Engineer

Engineering | Mountain View, United States or Remote | Remote, Remote | San Francisco, United States | Seattle, United States

Apply for this job

Working at Atlassian

Atlassians can choose where they work – whether in an office, from home, or a combination of the two. That way, Atlassians have more control over supporting their family, personal goals, and other priorities. We can hire people in any country where we have a legal entity. Interviews and onboarding are conducted virtually, a part of being a distributed-first company.

Be the backbone of Atlassian’s Agentic AI Integration Products : The Agentic AI Integrations team is responsible for the industry-leading Rovo MCP Server, Agent to Agent integrations as well as on the mission to catapult  Atlassian value by leveraging cutting-edge AI capabilities like Claude Skills, ChatGPT/Claude Apps etc., essentially we will be working on anything and everything with AI integrations into the Atlassian ecosystem.

Knack to work on bleeding-edge AI technologies: Passionate to explore and learn  AI transformative  technologies and  quickly pivot from prototyping new initiatives to building highly-scalable enterprise-grade AI products that will be used by 1000s of developers and enterprise users.

ML performance, quality, and systems acumen-ship: Experience in tuning MCP or agent-facing servers for latency, reliability, token efficiency, and tool-selection quality; including dynamic tool discovery, context and response optimization, observability, automated evals, and semantic retrieval using embeddings, vector search, hybrid ranking, and reranking.

* Design, build, and evolve MCP servers, tools, and agent-facing APIs with concise schemas, predictable errors, safe mutations, and clear outcome-oriented contracts.

* Develop accessible, responsive, and performant React and TypeScript experiences that make agent capabilities, MCP tools, and A2A interactions easy to discover, configure, and use.

* Build reusable components, design-system patterns, and frontend architecture that support consistent, scalable user experiences across AI-powered products.

* Integrate GraphQL and REST APIs, SDKs, streaming responses, and real-time data into reliable, user-friendly AI workflows.

* Optimize token and context efficiency through dynamic tool discovery, lazy loading, bounded responses, pagination, selective field retrieval, caching, and reduced tool-call loops.