Staff AI Inference Tools Engineer
Core
Build developer tools for AI inference deployments, including profiling, tracing, debugging, and agent-native workflows to improve developer experience.
Role type
Staff IC AI Inference Tools Engineer
Builds
Developer tools, observability systems, and agent-native workflows for AI inference
Domain
AI/ML Infrastructure, Systems Programming
Deliverable
production ML models
Required skills
Python, Mojo, Rust, C++, Go, system performance profiling, tracing, benchmarking, developer tooling design, kernel/model/serving integration
Preferred skills
GPU performance tooling, PyTorch, JAX, TensorFlow, AI-agent tooling (agent skills, MCP)
Technologies
Mojo, Rust, C++, Python, Go, PyTorch, JAX, TensorFlow
Responsibilities
Develop profiling, tracing, and debugging technologies for AI inference; create agent-native tools for model deployment and system triaging; strengthen interfaces between MAX, Mojo, and driver APIs; participate in design discussions and code reviews; collaborate with kernel, model, and serving engineers to improve productivity
Seniority
Staff, hands-on IC with mentorship
