Software Engineer, Triton Compiler

Details

Our mission at OpenAI is to discover and enact the path to safe, beneficial AGI. To do this, we believe that many technical breakthroughs are needed in generative modeling, reinforcement learning, large scale optimization, active learning, among other topics.

About the Role

As a Software Engineer, you will help build AI systems that achieve levels of performance that were previously impossible. This means strong engineering fundamentals — designing and optimizing core ML systems, writing highly reliable low-level code, and advancing the algorithms and infrastructure that power our models. The end goal in every project is the same: push the frontier forward.

The Compiler/Kernels team is responsible for the performance-critical software stack that brings OpenAI's custom silicon to life. We design and build the compilers, languages, and high-performance kernels that allow researchers to fully exploit our first-party accelerators. This includes advancing Triton and its backend, developing new compiler passes, and creating the tooling needed to write fast, correct, and deeply optimized kernels for brand-new hardware. We partner closely with the hardware team to unlock new capabilities and ensure our custom silicon can support the next generation of frontier models.

If you love compilers, kernels, and shaping how entirely new AI hardware is programmed, this role is for you. We're looking for engineers who are self-directed, comfortable in ambiguous technical spaces, and excited to identify and solve the highest-leverage problems.

Responsibilities

• Design and optimize core ML systems and performance-critical software.
• Develop and improve compilers, compiler passes, and backends (including advancing Triton and its backend).
• Build high-performance kernels and the tooling needed to write fast, correct, and deeply optimized kernels for new hardware.
• Work closely with hardware teams to expose and exploit capabilities of custom accelerators.
• Own problems end-to-end, including learning new hardware and software domains as needed.

Requirements

• 3+ years of relevant engineering experience, ideally in systems, compilers, ML frameworks, or performance engineering.
• Experience with compilers, kernels, or performance-critical software stacks.
• Comfort writing reliable low-level code and optimizing for performance on specialized hardware.
• Ability to work in ambiguous technical spaces and independently identify high-leverage problems to solve.
• Bonus: contributions to ML frameworks (e.g., PyTorch, JAX, TensorFlow) or compilers (e.g., LLVM, MLIR, XLA), or experience programming custom or specialized accelerators.

Benefits

• Base pay range listed separately; offers include equity and potential performance-related bonus(es).
• Medical, dental, and vision insurance with employer contributions to Health Savings Accounts.
• Pre-tax accounts for Health FSA, Dependent Care FSA, and commuter expenses.
• 401(k) retirement plan with employer match.
• Paid parental leave, paid medical and caregiver leave, flexible PTO, paid company holidays, and sick/safe time per applicable laws.
• Mental health and wellness support; employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily meals in offices and meal delivery credits as eligible.
• Relocation support for eligible employees.
• Additional fringe benefits such as charitable donation matching and wellness stipends may be provided.

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of AI capabilities and seek to safely deploy them through our products. We are an equal opportunity employer and are committed to providing reasonable accommodations to applicants with disabilities.