Software Engineering • Mid-Level

Who you are

You have a strong background in software engineering with a focus on performance optimization and distributed systems — you've worked on scaling infrastructure and have experience with GPU platforms. Your expertise in Python and CUDA allows you to develop efficient solutions for complex problems. You thrive in collaborative environments, working closely with research and infrastructure teams to ensure high-performance execution of AI models.

You possess a deep understanding of model inference and have experience integrating internal model-serving infrastructure into GPU-backed systems. Your problem-solving skills enable you to debug and optimize distributed inference workloads across various layers, including memory, network, and compute. You are familiar with frameworks like Triton and have a passion for advancing inference performance on AMD accelerators.

What you'll do

In this role, you will own the bring-up, correctness, and performance of the OpenAI inference stack on AMD hardware. You will collaborate with partner teams to design and optimize high-performance GPU kernels, ensuring that our largest models run smoothly on new hardware. Your responsibilities will include validating the correctness, performance, and scalability of model execution on large GPU clusters, as well as integrating internal model-serving infrastructure into a variety of systems.

You will work across the stack, from low-level kernel performance to high-level distributed execution, and will be instrumental in shaping OpenAI's multi-platform inference capabilities. Your contributions will directly impact the efficiency and effectiveness of our AI models, empowering consumers, enterprises, and developers to leverage cutting-edge technology.

What we offer

At OpenAI, we believe in the potential of artificial intelligence to solve global challenges. We offer a collaborative work environment where you can grow your skills and make a significant impact. Join us in shaping the future of technology and enjoy the opportunity to work with some of the brightest minds in the field. We are committed to providing reasonable accommodations to applicants with disabilities and encourage you to apply even if your experience doesn't match every requirement.