This position is expected to start around January 2026 and continue through the Winter/Spring term (approximately April 2026) or into Summer 2026 if available and there is an opportunity to do so. We ask for a minimum of 12 weeks, full-time and on-site, for most internships. Our internship program is for students who are actively enrolled in an academic program. Recent graduates seeking employment after graduation and not returning to school should apply for full-time positions, not internships. The AI inference co-design team's goal is to take research models and make them run efficiently on our AI-ASIC to power real-time inference for Autopilot and Optimus programs. This unique role lies at the intersection of AI research, compiler development, kernel optimization, math and HW design. You will work extensively with AI engineers and come up with novel techniques to quantize models, improve precision and explore non-standard alternate architectures. You will be developing optimized micro kernels using a cutting-edge MLIR compiler and solve the performance bottlenecks needed to achieve real-time latency needed for self-driving and humanoid robots.