Tech Stack
Tag name is followed by "@" symbol and proficiency level value.
About proficiency levels:
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
AI @ 3
Distributed Systems @ 3
Machine Learning
Observability
Performance Optimization @ 3
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
Details
About the Team
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.
About the Role
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.
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.
Requirements
You might thrive in this role if you have:
- 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.
About OpenAI
OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products.