Software Engineer, Model Inference
San Francisco
Workplace: OnsiteFull timeUSD 325,000 - 490,000 annuallyFunction: Software EngineeringExperience: 5+ yearsSkills: ["Problem-solving","Collaboration","Ownership","Communication","Teamwork"]Join OpenAI’s Inference team to optimize world-leading AI models for high-volume, low-latency production and research environments. You will collaborate with ML researchers and engineers to push the latest technologies into production, improve inference performance, and build tools to diagnose bottlenecks while maximizing GPU utilization on Azure. Expect ownership of end-to-end problems and contributions to scalable distributed systems.
Loading
Loading job details...
Preparing the role view and application actions.

