SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
OpenAI's Foundations Research team is seeking a Research Scientist to lead Search Integrity—systems designed to distinguish useful web content from spam, manipulation, and adversarial material. This role sits within the Search team, which co-designs model-system interfaces for agentic search, focusing on serving, indexing, and retrieval at scale.
You will define the technical direction for Search Integrity, identifying gaps and prioritizing problems and interventions. The core challenge extends beyond evaluating individual pages; you must detect coordinated manipulation across links, metadata, and relationships between sites. As AI makes convincing content easier to produce at scale, detection systems must evolve to counter increasingly sophisticated adversaries.
Key responsibilities include:
- Defining technical direction for Search Integrity and determining which problems to prioritize
- Developing AI/ML systems to detect spam, scams, phishing, malicious domains, prompt injections, and low-quality web content
- Discovering useful signals across page content, links, domains, metadata, and site relationships to reveal coordinated manipulation
- Building evaluations that measure detection quality and how integrity interventions affect information retrieval
- Translating detection signals into indexing, ranking, and filtering decisions
- Serving as technical owner for integrity within Search, partnering with researchers, engineers, and Safety/Integrity teams
You will work closely with Search and broader Safety and Integrity teams, using frontier models to advance detection methods and bring them into production. This is a hands-on technical role requiring independent problem definition and execution from experimentation through deployment.
QUALIFICATIONS:
- Deep experience in web spam, search quality, adversarial content detection, or related integrity problems at scale
- Strong applied ML and research skills, with experience developing classifiers, detection methods, and evaluations for real-world systems
- Understanding of how adversaries manipulate content and links, coordinate across sites, and adapt to detection systems
- Track record of independently defining ambiguous technical problems and driving solutions from experimentation through production
- Experience working across research, engineering, and integrity teams while remaining hands-on with technical work
- First-principles approach to using frontier models and compute, with strong interest in keeping detection systems effective as adversaries evolve
