Research Scientist / Research Engineer, Search - Knowledge Graphs
$380k - $850k • Remote • San Francisco • FullTime
Posted 12h ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Research Engineer
About the job
The Foundations Research team is focused on high-impact, forward-looking AI research, particularly for future frontier models. Within this team, the Search group is developing agentic search capabilities by co-designing model-system interfaces with the core search stack, including serving, indexing, and retrieval. We build and research large-scale systems to transform and index vast amounts of data, enabling AI models to effectively find and reason over information.
This role involves researching and developing methods for extracting and utilizing semi-structured knowledge graphs from heterogeneous web content. The core objective is to make this information more accessible and useful for AI models, addressing key questions about the optimal structure for information retrieval, scalable extraction techniques, and how to measure and improve model reasoning capabilities. You will collaborate across research, data, and systems to advance how knowledge is extracted, organized, and retrieved, with potential for scientific publication and impact across OpenAI products.
Responsibilities
- Develop methods to extract and connect structured information (entities, attributes, relationships) from diverse web sources.
- Build scalable approaches to transform noisy web content into useful knowledge representations.
- Explore how AI and compute can enhance extraction quality and reduce manual effort in knowledge systems.
- Design evaluations to measure the quality and usefulness of extracted knowledge for retrieval and model reasoning.
- Partner with researchers and engineers to integrate structured knowledge into Search and use performance feedback for improvements.
Requirements
- Deep experience in knowledge extraction, knowledge graphs, entity resolution, or deriving structure from large, heterogeneous datasets.
- Strong machine learning and research skills with experience developing and evaluating methods on real-world data.
- Track record of building or scaling data and ML systems, especially for web-scale extraction, indexing, or retrieval.
- Experience independently driving open-ended technical problems from ideation through implementation.
- First-principles approach to AI and compute, with a willingness to rethink established methods.
- Strong interest in how information representation impacts model understanding and utilization.