Software Engineer, Foundations Retrieval

OpenAI • San Francisco, CA

1d

About The Position

The Foundations Research team works on high-risk, high-reward ideas that could shape the next decade of AI. Our goal is to advance the science and data that enable our training and scaling efforts, with a particular focus on future frontier models. Pushing the boundaries of data, scaling laws, optimization techniques, model architectures, and efficiency improvements to propel our science.
The Search team sits within Foundations, building agentic search by co-designing model–system interfaces with the core search stack (serving, indexing, retrieval) to translate model intent into reliable, real-world actions. Operating at the frontier of AI and information retrieval, the team develops large-scale systems that transform and index vast corpora, enabling models to reason over global knowledge and act dependably. In close partnership with researchers, we rapidly bring modeling breakthroughs into production and redefine how intelligent systems discover, retrieve, and synthesize information at planetary scale.
We’re looking for a Software Engineer focused on building and scaling retrieval systems. You’ll work with a team of researchers and engineers to develop infrastructure that enables models to retrieve and act on the right information at the right time. This includes designing and operating indexing systems, retrieval pipelines, and serving layers.
This work supports retrieval across OpenAI products and research, with direct impact on system performance, reliability, and scale.

Requirements

• Experience building and scaling distributed systems.
• Background in search, retrieval, or indexing systems.
• Familiarity with embedding-based or ML-powered systems.
• Experience with performance optimization and production reliability.
• Ability to work across ML and systems boundaries.
• First-principles thinking in ambiguous problem spaces.

Responsibilities

• Build and scale retrieval infrastructure across indexing, serving, and query execution.
• Develop low-latency, high-throughput systems for real-time model interaction.
• Partner with research to productionize embedding and retrieval techniques.
• Support dense, sparse, and hybrid retrieval pipelines.
• Own system performance, reliability, and observability at scale.
• Collaborate across Pretraining, Inference, and Product teams to integrate retrieval end-to-end.
• Contribute to model - system interfaces for agentic workflows.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed