Software Engineer - Compiler, Kernels, Runtime

OpenAI is seeking a skilled Software Engineer to join their Scaling team, focusing on compiler development, kernel optimization, and runtime systems. This role is central to building and optimizing the low-level stack that powers OpenAI's ML training infrastructure across their supercomputing clusters.

The position offers an exciting opportunity to work at the intersection of systems programming, ML infrastructure, and high-performance computing. You'll be responsible for designing high-performance runtimes, building custom kernels, contributing to compiler infrastructure, and developing scalable simulation systems. The role requires balancing user-friendly developer APIs with highly efficient runtime systems.

As part of the Scaling team, you'll be instrumental in developing foundational components that maximize the productivity of researchers and hardware utilization. The team's mission is to accelerate progress toward AGI by enabling the fastest iteration cycles and highest throughput for model development at scale.

The role offers a competitive compensation package ranging from $310K to $550K, plus equity and comprehensive benefits including medical, dental, and vision insurance, mental health support, and a 401(k) with 50% matching. The position is based in San Francisco with a hybrid work model (3 days/week in-office), and relocation assistance is available.

Ideal candidates should have deep expertise in systems programming languages like Rust and C++, along with Python proficiency. Experience in compiler development, kernel authoring, accelerator programming, or high-performance simulation is highly valued. The role requires someone who thrives in a fast-paced environment and is passionate about optimizing large-scale systems.

Working at OpenAI means joining a company at the forefront of AI development, with a strong commitment to ensuring AI benefits humanity. The company offers a collaborative environment where you'll work with cutting-edge technology and contribute to groundbreaking advancements in artificial intelligence.