Protection Scientist Engineer, Integrity

The role

Protection Scientists design and maintain systems of defence against usage harms enabled by OpenAI products. You will build harm detection systems, develop signals and classifiers, and lead cross-functional protection strategies.

What you will do

• Define and drive protection strategy for a harm area or launch.
• Build and maintain harm detection using SQL, Python, machine learning and language models.
• Lead cross-functional execution and resolve technical and organisational dependencies.
• Investigate emerging harms and abuse patterns.
• Evaluate and improve the complete system of defence.
• Protect product and model launches by defining requirements and monitoring.
• Scale approaches with language models, agents and reusable tools.

Required qualifications

• Deep expertise in at least one relevant harm domain developed through integrity, trust and safety, security, investigations or related work.
• Proficient in SQL and Python.
• Experience writing reliable and efficient production code for detection and data processing.
• Ability to apply quantitative analysis and machine-learning methods to measure risks and evaluate system effectiveness.
• Experience setting strategy and delivering complex, cross-functional technical projects.
• Communicate clearly and concisely in writing and conversation.
• Ability to use language models and other automation to scale work.

Nice to have

• Additional ML or SWE experience
• Additional DS/measurement background

Before you apply

• Participation in an on-call rotation that may involve resolving urgent escalations outside normal working hours.
• Some investigations may involve sensitive content, including sexual, violent or otherwise disturbing material.
• Background checks for applicants will be administered in accordance with applicable law.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.