Internship, Software Engineer, AI Compiler (summer 2026)

Tesla Tesla · Auto · Palo Alto, CA · Tesla AI

Software Engineer Intern focused on the AI inference stack, including compiler and runtime development for Tesla's vehicles and robots. Responsibilities include writing, debugging, and maintaining software, designing APIs and DSLs, supporting ML framework integration, and optimizing performance on Tesla's hardware. Requires experience with ML compilers/runtimes and DSLs.

What you'd actually do

  1. Write, debug and maintain robust software for Tesla AI inference (Compiler / Runtime) across FSD, Optimus, and Data Center use-cases
  2. Provide AI developers access to performance-critical hardware features through new APIs and Domain-Specific Languages (DSLs)
  3. Design APIs, compiler and runtime features enabling distributed inference on Tesla’s hardware
  4. Support the integration of our deployment stack with ML frameworks (PyTorch, JAX)
  5. Keep up-to-date and collaborate with ML/compiler open-source community

Skills

Required

  • ML compilers/runtimes (e.g. MLIR, LLVM, XLA, PJRT, TensorRT)
  • Development of Domain-Specific Languages (DSLs) like Triton, cuTile, Pallas
  • CPUs, GPUs and modern AI accelerators
  • Computer architecture, distributed systems, networking, and collectives
  • ML frameworks (PyTorch, JAX), with a focus on framework internals
  • Proficient C/C++ programming C/C++ including modern C/C++ (C++14/17/20)
  • Basic Python proficiency
  • Modern ML architectures

Nice to have

  • AI developers
  • performance-critical hardware features
  • APIs
  • Domain-Specific Languages (DSLs)
  • distributed inference
  • ML frameworks
  • PyTorch
  • JAX
  • ML/compiler open-source community
  • massively parallel systems
  • autonomous vehicles
  • robots
  • offline inference

What the JD emphasized

  • AI inference stack
  • compiler/runtime
  • ML compilers/runtimes
  • Domain-Specific Languages (DSLs)

Other signals

  • AI inference stack
  • compiler/runtime
  • extract maximum performance
  • production models
  • MLIR compiler
  • runtime architecture
  • optimization approaches
  • code generation
  • Tesla's hardware
  • FSD
  • Optimus
  • Data Center use-cases
  • APIs
  • DSLs
  • distributed inference
  • ML frameworks
  • PyTorch
  • JAX
  • ML/compiler open-source community
  • massively parallel systems
  • autonomous vehicles
  • robots