•San Francisco, California, USA
About the team The ChatGPT Capacity and Optimization team manages the largest LLM inference fleet on planet earth. We serve over 100M weekly active users the best model experience at the lowest latency. As the ChatGPT user-base scales, so too does the footprint of the inference fleet, and so too must our sophistication in how we deliver the most value to our users with the resources we have available, which is one of our biggest drivers for further growing our user-base. About this role We're