Software Engineer, Search Infrastructure
OpenAI · San Francisco
About this role
**Software Engineer, Search Infrastructure** **About the Team** The Search Product Infrastructure team builds systems powering search experiences across ChatGPT, partnering with model, inference, and search index teams to bring advances into production. **About the Role** Design, build, and operate systems connecting models with search at ChatGPT scale. Own projects from technical design through launch, tackling search orchestration, inference efficiency, experimentation, and production reliability. **Location:** San Francisco, CA (Hybrid - 3 days/week in office) **Key Responsibilities** • Design services coordinating search classification, retrieval, ranking, and model inference • Improve latency, throughput, and efficiency through profiling, caching, and capacity planning • Build experimentation tooling for A/B testing and production validation • Own production reliability through observability and incident response • Build search APIs enabling models and agents to retrieve information reliably **Ideal Candidate** • Significant experience designing and operating large-scale distributed systems • Background in search, information retrieval, ML infrastructure, or inference serving • Strong programming and systems debugging skills across multiple languages • Ability to translate ambiguous needs into clear technical plans • Enjoys learning across systems and ML domains **About OpenAI** AI research and deployment company dedicated to ensuring general-purpose AI benefits all of humanity. Equal opportunity employer.
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.