Research Scientist / Research Engineer, Safety + Alignment, Search
$380k - $850k • Remote • San Francisco • FullTime
Posted 7d ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
Machine Learning Engineer
About the job
We are seeking a Researcher to lead our safety and alignment research, focusing on building systems that can distinguish valuable web content from spam, manipulation, and other adversarial or low-quality material. This role involves tackling the challenge of detecting coordinated manipulation that may not be apparent when evaluating individual pages in isolation. As AI advances the ease of producing convincing content at scale, you will be responsible for adapting detection systems to counter increasingly sophisticated adversaries. You will define the technical strategy, develop classifiers and evaluations, and influence how integrity signals shape Search's indexing and retrieval processes. Collaborating closely with Search and broader Safety and Integrity teams, you will leverage frontier models to enhance detection methods and implement them in production.
Responsibilities
- Define the technical direction for Safety + Integrity, identifying gaps and prioritizing problems and interventions.
- Develop AI and ML systems to detect spam, scams, phishing, malicious domains, prompt injections, and other adversarial or low-quality web content.
- Discover signals across page content, links, domains, metadata, and website relationships, including patterns of coordinated manipulation.
- Build evaluations to measure detection quality and the impact of integrity interventions on Search results.
- Translate detection signals into indexing, ranking, and filtering decisions to improve model retrieval and reliability.
- Serve as the technical owner for integrity within Search, partnering with researchers and engineers to build and deploy systems.
Requirements
- 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 to 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 a strong interest in keeping detection systems effective against evolving adversaries.