← All roles

Protection Scientist Engineer, Integrity

OpenAI· Applied AI
Apply on company site
London, UKFull-timePosted 11mo ago

About the role

Protection Scientists design, orchestrate, and mature systems of defence against usage harms enabled by OpenAI's products. They blend harm domain expertise with investigation, data science, machine learning, policy and operations to detect and mitigate harmful activity, scale protections for product launches, and drive cross-functional delivery.

Responsibilities

  • Define and drive protection strategy for a harm area or launch. Translate ambiguous risks into goals, priorities and roadmaps, and make trade-offs based on evidence, risk and available capacity.
  • Directly build and maintain harm detection. Develop production signals, classifiers and pipelines using SQL, Python, machine learning and language models, integrating with shared engineering platforms.
  • Lead cross-functional execution. Translate between specialist roles, establish shared understanding and ownership, resolve technical and organisational dependencies, and communicate recommendations and specific asks clearly.
  • Investigate emerging harms and abuse patterns. Work with world class domain experts to distinguish harmful activity from legitimate use, develop detection criteria, and inform policies and review protocols with Policy and Operations partners.
  • Evaluate and improve the complete system of defence. Measure remaining harm, detection quality and intervention effectiveness and collaborate with Data Science on more sophisticated metrics.
  • Protect product and model launches. Define data, detection and review requirements; establish monitoring; investigate gaps and critical escalations; and drive improvements informed by post-launch findings.
  • Scale effective approaches with language models, agents and reusable tools. Choose where automation and human judgement are needed, and build documentation and processes that improve reliability and help others extend the work.

Qualifications

  • Think in systems across technical, analytical, investigative and operational disciplines.
  • Bring deep expertise in at least one relevant harm domain (integrity, trust and safety, security, investigations or related work).
  • Proficient in SQL and Python; experience writing reliable, production-grade code for detection and data processing; additional ML or SWE experience is a plus.
  • Ability to apply quantitative analysis and machine-learning methods to measure risks and evaluate system effectiveness; understanding data limitations, missed harms, false positives and interventions.
  • Experience setting strategy and delivering complex cross-functional technical projects.
  • Clear and concise written and verbal communication; ability to explain technical findings and surface trade-offs.
  • Experience using language models and automation to scale analytical, investigative or operational work with appropriate human oversight.

Skills

Required:SQLPythonInvestigation and domain expertiseCross-functional leadership
Nice to have:Machine Learning
Last updated Oct 1, 2026. Interested? Apply on the company site.

About OpenAI

ai-infrastructure-and-developmentliquid-ai-recruiting-targetllmsetter-30setter-30-2026-q1speech-to-texttext-to-speechvoice-ai-stack
Company profileWebsite

More open roles at OpenAI