Tesla Software Engineer Runtime AI Inference 

United States, California, Palo Alto 

118260329

As a Software Engineer within our Autonomy teams, you will contribute to one of the most advanced and widely deployed AI Platforms in the world for Autopilot and our Humanoid Robot, Optimus.

In this role, you will be responsible for the internal working of the AI inference stack and runtime running neural networks in millions of Tesla vehicles and Optimus, collaborating closely with the AI Engineers and Hardware Engineers. The nature of the role is multi-disciplinary - you will be working at the intersection of machine learning and systems. You will build the frameworks and infrastructure that enable the seamless deployment, integration, and inference of all neural networks. You will develop system tools to benchmark, characterize, and optimize the latency and throughput of AI workloads on the FSD chip.

• Write, debug and maintain robust software for Autopilot and Humanoid robot AI inference (Export / Compiler / Runtime) stack
• Work with AI/compiler/OS/driver teams to enable efficient execution of the AI Models
• Low level systems programming including (not limited to) - GPU kernels, asynchronous / multithreaded programming, etc.

• Proficient C/C++ programming C/C++ including modern C/C++(C++14/17/20)
• Basic Python proficiency
• Parallel programming with CUDA, OpenCL, or SIMD, withprevious experience with custom ASIC / hardware accelerator chips, is a plus.
• Familiarity with ML runtimes, compilers, or frameworks isa plus. (e.g. PJRT, MLIR, XLA, TensorRT, LLVM, JAX, TVM)
• Bachelor's Degree in Computer Science, Physics, Computer Engineering,Electrical Engineering or proof of exceptional skills in related fields withpractical software engineering experience