Research Scientist / Research Engineer, Search - Knowledge Graphs

OpenAI • San Francisco, CA

2d • $380,000 - $850,000

About The Position

The Foundations Research team pursues high-risk, high-reward ideas that could shape the next decade of AI, advancing the science and data supporting training and scaling, with a focus on future frontier models. The team works on data, scaling laws, optimization techniques, model architectures, model-and-search co-design, and efficiency improvements.

Within Foundations, the Search team builds agentic search by co-designing model-system interfaces with the core search stack, including serving, indexing, and retrieval. It researches and develops large-scale systems for transforming and indexing vast corpora so models can find and reason over information effectively.

The role focuses on semi-structured knowledge graphs within Search. The researcher will develop methods for mining structured information from heterogeneous, unstructured, and semi-structured web content, making it more accessible and useful to AI models. The work spans research, data, and systems, investigating how AI and compute can improve knowledge extraction, organization, and retrieval. It will support retrieval across OpenAI products and internal research efforts, with opportunities for scientific publication.

Requirements

• Deep experience in knowledge extraction, knowledge graphs, entity resolution, or related work deriving structure from large, heterogeneous datasets.
• Strong machine learning and research skills, with experience developing and evaluating methods for real-world data.
• A track record of building or scaling data and ML systems, particularly for web-scale extraction, indexing, or retrieval.
• Experience independently driving open-ended technical problems from an initial idea through experimentation and implementation.
• A first-principles approach to using AI and compute, with willingness to rethink established methods as model capabilities improve.
• Strong interest in how the representation of information shapes what models can find, understand, and use.

Responsibilities

• Develop methods to extract and connect structured information across diverse web sources, including entities, attributes, and relationships.
• Build scalable approaches for transforming noisy, inconsistent content into useful knowledge representations.
• Explore how models and compute can improve extraction quality and reduce manual work in building knowledge systems.
• Design evaluations that measure the quality of extracted knowledge and its usefulness for retrieval and model reasoning.
• Partner with researchers and engineers to integrate structured knowledge into Search and use model performance to guide improvements.

What This Job Offers

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