OpenAI
Research Scientist / Research Engineer, Safety + Alignment, Search
$380K–$850K
San Francisco · Full-time · Posted Oct 21, 2026
About the job
Lead safety and alignment research for Search, developing systems that identify adversarial and low-quality web content and influence what Search indexes and retrieves.
What you'll do
- Set technical direction and prioritize Safety + Integrity problems and interventions.
- Develop detection systems and evaluations for spam, scams, phishing, malicious domains, prompt injections, and coordinated manipulation.
- Translate integrity signals into indexing, ranking, and filtering decisions and partner with teams to deploy these systems.
What they ask for
- Deep experience in web spam, search quality, adversarial content detection, or related integrity problems at scale.
- Strong applied ML and research skills, including 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.
Pay
$380K – $850K USD base salary
AI focus
Use frontier models to advance detection methods and build AI/ML systems that identify adversarial or low-quality web content.
Model-written summary · the original posting is authoritative