Protection Scientist Engineer, Integrity
AI research and deployment company building and deploying frontier AI products, including ChatGPT, Codex, and its API platform.
Projects
About OpenAI
OpenAI’s mission is to ensure artificial general intelligence benefits all of humanity. It consists of the nonprofit OpenAI Foundation and OpenAI Group, a public benefit corporation governed by the Foundation.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design, build, evaluate and maintain production harm detection systems, developing signals, classifiers and pipelines with SQL, Python, machine learning and language models. You will also own protection strategy and cross-functional delivery for a harm area or product launch, investigate emerging abuse patterns, and measure and improve the system of defence. The role includes an on-call rotation and exposure to sensitive content.
Requirements
- Systems thinking across technical, analytical, investigative and operational disciplines
- Deep expertise in at least one harm domain such as integrity, trust and safety, security or investigations
- Proficiency in SQL and Python and production code experience
- Quantitative analysis and machine learning methods
- Experience setting strategy and delivering complex cross-functional projects
- Clear written and verbal communication
- Ability to use language models and automation at scale
Responsibilities
- Define and drive protection strategy for a harm area or launch
- Build and maintain harm detection signals, classifiers and pipelines
- Lead cross-functional execution and resolve dependencies
- Investigate emerging harms and abuse patterns
- Evaluate and improve the system of defence
- Protect product and model launches
- Scale approaches with language models, agents and reusable tools
- Participate in an on-call rotation
