Internship, Software Engineer, Core SI Compiler & Runtime (Winter/Spring 2027)

What to Expect

Consider before submitting an application:

This position is expected to start January 2027 and continue through spring term (ending approximately April 2027) or continuing into Summer 2027 if available and there is an opportunity to do so. We ask for a minimum of 12 weeks, full-time (40 hours/week) 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.

International Students: If your work authorization is through CPT, please consult your school on your ability to work 40 hours per week before applying. You must be able to work 40 hours per week on-site. Many students will be limited to part-time during the academic year. Our internship program places high-caliber students on teams where their work is visible and critical.

You will design and build the compiler and runtime that power one of the most advanced and widely deployed AI platforms on Earth—running neural networks in millions of Tesla vehicles and Optimus robots. Full control of the hardware means you co-design the software stack to extract maximum performance, latency, and efficiency that generic frameworks cannot reach. Production models directly drive priorities: every optimization you ship immediately enables more capable autonomy, more complex robot behaviors, and higher-throughput data-center inference. This is first-principles systems work at the metal including deleting unnecessary abstractions, inventing high performance APIs and DSLs, and closing the loop between silicon capabilities and real-world AI at an unprecedented scale.

What You’ll Do

• Write, debug, and maintain robust compiler and runtime software for Tesla AI inference across FSD, Optimus, and data-center workloads
• Give AI developers direct access to performance-critical hardware features through new APIs and domain-specific languages
• Design compiler and runtime features that enable efficient distributed inference on Tesla hardware
• Integrate the deployment stack with modern ML frameworks (Py Torch, JAX) while keeping the path to silicon as short and efficient as possible
• Analyze and resolve functional and performance issues on massively parallel systems
• Deploy and optimize AI models that run in autonomous vehicles, humanoid robots, and offline inference pipelines where results show up in the real world

What You’ll Bring

• Pursuing a degree in Computer Science, Computer Engineering, or a relevant field of study with an expected graduation day 2028 or earlier
• Demonstrated expertise with ML compilers and runtimes (MLIR, LLVM, XLA, PJRT, TensorRT, or equivalent)
• Experience developing domain-specific languages or high-performance programming models (Triton, cu Tile, Pallas, or similar).
• Strong familiarity with CPUs, GPUs, and modern AI accelerators
• Deep knowledge of computer architecture, distributed systems, networking, and collectives
• Proficiency in modern C++ and solid systems programming skills