Staff AI Inference Tools Engineer

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Improve the MAX developer experience by providing tools for both traditional and agentic workflows.

• Expose data throughout the entire AI stack while supporting various hardware platforms.

• Design, develop, and maintain profiling and tracing tools.

• Create debuggers and tools for verifying correctness.

• Develop metrics and dashboards to assess the performance and health of MAX deployments.

• Build agent-native tools and facilitate agentic workflows.

• Write agents to initialize models, address running-system issues, and profile and optimize actual workloads.

• Integrate MAX tools across MAX, Mojo, driver APIs, and orchestration layers.

• Engage in design discussions and participate in code reviews.

• Collaborate closely with kernel, model, and serving engineers to transform persistent pain points into improved tools.

⛳️ Requirements

• A strong passion for creating outstanding developer experiences.

• Proven experience in designing, building, and delivering developer tools, infrastructure, or observability systems.

• Proficiency in one or more systems/performance programming languages such as C++, Rust, or Go.

• Proficiency in one or more user-facing programming languages like Python; familiarity with Mojo is advantageous.

• Experience in measuring software performance using profiling, tracing, or benchmarking techniques.

• Knowledge of systems to analyze performance outcomes.

• Excellent written communication skills and the ability to work independently within a distributed team.

• A user-centered approach with the ability to understand users' workflows.

• A Bachelor's degree in Engineering, Information Systems, Computer Engineering, Electrical Engineering, Computer Science, or a related field, along with 4+ years of Software Engineering or relevant work experience; OR a Master's degree and 3+ years; OR a PhD and 2+ years.

• Minimum of 2 years of professional experience with a programming language such as Python, Mojo, Rust, C++, etc.

• Candidates must be based in the UK.

• GPU performance tooling or GPU programming experience is beneficial but not mandatory.

• Familiarity with basic AI implementation and modeling techniques, as well as knowledge of PyTorch, JAX, or TensorFlow, is helpful but not required.

• Experience in building tools for AI agents, including agent skills or MCP, is advantageous but not essential.

🏝️ Benefits

• Comprehensive healthcare coverage.

• Retirement and savings programs.

• Opportunities for employee stock purchases.

• Paid time off.

• Resources for wellbeing.

• Programs supporting families.

• Opportunities for learning and development.

• RSU grants.

• Annual target bonus.

• Regular team onsite meetings and local gatherings.

• Travel 2–4 times a year for all positions.