Tesla

Makes electric cars, robotaxis and grid batteries

Software Engineer - Core SI Compiler & Runtime, Pre-Silicon

Systems Software EngineeringConfirmed live in the last 24 hours

Full-timePalo Alto, CA, USANo salary listedIn-person

About the Job

Requirements

Demonstrated expertise building or extending machine-learning compilers or runtimes, such as MLIR, LLVM, XLA, PJRT, or TensorRT.
Experience designing or implementing performance-oriented domain-specific languages or programming models, such as Triton, Pallas, or cuTile-style systems.
Strong modern C++ and solid systems programming skills.
Deep familiarity with CPUs, GPUs, and modern SI accelerators, including the ability to reason about computer architecture, memory hierarchies, parallelism, and performance bottlenecks at a fundamental level.
Comfort debugging complex functional and performance issues across software and simulated hardware.
Preference for first-principles design over layering more software on existing frameworks, and a drive to work on hard problems at scale.
A degree in Engineering or Computer Science, or equivalent experience and evidence of exceptional ability.

Responsibilities

Own critical pieces of the pre-silicon compiler and runtime for custom SI accelerators, including SI5, SI6, and future generations.
Develop MLIR/LLVM backends, code generation, and optimization passes that map neural networks onto architectures still under design.
Create new APIs and domain-specific languages so model developers can express intent that maps efficiently onto the hardware.
Drive performance and functional correctness on massively parallel systems before tape-out using simulators, emulators, and early silicon bring-up.
Close the loop with production models for FSD, Optimus, and data centers that dictate what the compiler must deliver next.
Collaborate daily with silicon architects, SI researchers, and systems engineers so that the code influences transistor-level decisions and vice versa.

Category	Tesla SI
Location	Palo Alto, California
Requisition ID	270299
Type	Full-time

Job Description

<p>You will design and build the compiler and runtime that turn Tesla’s next-generation SI silicon into the highest-performance, highest-volume inference engines on the planet. This stack already powers neural networks in millions of vehicles and will enable unsupervised autonomy, Optimus at scale, and data-center workloads. Working pre-silicon means the hardware does not exist yet—your decisions shape both the silicon and the software that extracts every useful operation from it. Hardware and software teams sit together, review designs weekly, and iterate on a multi-month cadence. Abstractions that hide performance are deleted. You invent the APIs, DSLs, and code-generation paths that give SI engineers direct, high-performance access to unique silicon capabilities. This is pure first-principles co-design at the absolute frontier of SI hardware and software. </p>

Job Responsibilities

Own critical pieces of the pre-silicon compiler and runtime for Tesla’s custom SI accelerators including SI5, SI6, and beyond
Develop MLIR/LLVM backends, code generation, and optimization passes that map neural networks onto architectures still under design
Create new APIs and domain specific languages so model developers can express intent that maps cleanly and efficiently onto the hardware
Drive performance and functional correctness on massively parallel systems long before tape out using simulators, emulators, and early silicon bringup
Close the loop with production models that will ship in FSD, Optimus, and data centers that directly dictate what the compiler must deliver next
Collaborate daily with silicon architects, SI researchers, and systems engineers so that your code influences transistor level decisions and vice versa

Job Requirements

Demonstrated expertise building or extending ML compilers/runtimes (MLIR, LLVM, XLA, PJRT, TensorRT, or equivalent)
Experience designing or implementing performance-oriented DSLs or programming models (Triton, Pallas, cuTile-style, or equivalent)
Strong modern C++ and solid systems programming skills
Deep familiarity with CPUs, GPUs, and modern SI accelerators; ability to reason about computer architecture, memory hierarchies, parallelism, and performance bottlenecks at a fundamental level
Comfort debugging complex functional and performance issues across software and simulated hardware
Preference for first principles design over layering more software on existing frameworks, and a drive to work on hard problems that matter at the highest possible scale
Degree in Engineering, Computer Science, or equivalent in experience and evidence of exceptional ability

About the Company

Tesla

Makes electric cars, robotaxis and grid batteries

Tesla makes electric cars and batteries that store power for homes and utilities, and it develops self-driving software and humanoid robots. In 2023, its Model Y became the first electric vehicle to rank as the world's best-selling car. Buyers order the Model 3 sedan, Model Y SUV, or Cybertruck pickup directly from Tesla instead of through dealers, and they charge on its Supercharger fast-charging network. It also sells Megapack and Powerwall batteries, runs a robotaxi service, and charges drivers a monthly fee for self-driving software that still needs their supervision. Tesla was founded in 2003, with Elon Musk as its lead early investor and a recognized co-founder, and it is based in Austin, Texas.

Company size: 10,001+
Company stage: IPO
Headquarters: Austin, TX
Founded: 2003

Recently Posted Jobs

Explore more opportunities at Tesla

See more jobs