Protection Scientist Engineer
Core
Design and build systems to proactively identify, monitor, and enforce against abuse on AI products, including new product launches and existing platforms.
Role type
Protection Scientist Engineer (AI Safety & Threat Intelligence)
Builds
Scaled detection, review, enforcement, and measurement systems for abuse risks
Domain
AI Safety, Threat Intelligence, Product Security
Deliverable
production ML models | product features
Required skills
SQL, Python, data querying and transformation, statistical analysis, investigative mindset, bad actor identification, cross-functional collaboration
Preferred skills
Machine learning and classification, process automation, experience with language models, working with scaled labellers, AI safety domain knowledge
Technologies
Python, SQL
Responsibilities
Scope and implement abuse monitoring requirements for new product launches; Improve processes to sustain monitoring operations for existing products; Prototype and mature into production systems of detection, review, and enforcement of abuse; Work with Product, Policy, Ops, and Engineering teams to address key risks
Seniority
Individual Contributor (IC), hands-on engineering and analysis
