Software Engineer, Inference - Multi Modal
San Francisco
Workplace: OnsiteFull timeFunction: Software EngineeringSkills: ["CPU/GPU optimization","Distributed systems","Scaling","Inference","Model deployment"]Join OpenAI’s Inference team to design and build high-performance inference infrastructure for multimodal models, delivering real-time audio, image, and other modalities at scale. Collaborate with researchers and product engineers to deploy state-of-the-art capabilities, optimize GPU-accelerated pipelines, and improve system-level performance like tensor parallelism and hardware abstraction layers.
Loading
Loading job details...
Preparing the role view and application actions.

