Protection Scientist Engineer, Integrity
- Level
- Mid
Not stated in the posting: salary, work type, visa.
Open. First seen 7 March 2026.
About the role
About the Team
The Integrity team is responsible for the scaled systems that help identify and respond to bad actors and harm on OpenAI’s platforms. We protect users and the wider world by developing responses to complex harms and building the harm protections needed for new product and model launches. Integrity’s work spans not only across frontier harms like biological weapons and cybersecurity, but also high severity abuses such as child safety, nation-state misuse, and violence.
About the Role
Protection Scientists within Integrity design, orchestrate, and mature systems of defence against usage harms enabled by OpenAI's products. We are systems thinkers that combine deep harm domain expertise with breadth across investigation, data science, machine learning, policy and operations. Our distinctive strength is understanding how these disciplines fit together and translating between them to design and build effective systems of defence.
In London, we are hiring for protection work focused on scams, suicide and self-harm, or jailbreaks. Depending on your domain expertise, you could build systems that detect AI-enabled fraud and deceptive activity, identify interactions that may facilitate or encourage suicide and self-harm, or investigate attempts to circumvent model safeguards. These areas require different approaches, from understanding adversarial tactics and victim targeting to applying careful contextual judgement to sensitive conversations and emerging patterns of model misuse.
Your core hands-on technical responsibility is harm detection. You will design, build, evaluate and maintain production detection systems, drawing on investigative expertise, data and shared engineering platforms. You will develop signals and classifiers that identify harmful activity and interactions accurately, and improve them as products, behaviour and patterns of use evolve.
You will also own the strategy and cross-functional delivery of protection work for a harm area or product launch. Working closely with investigators and other domain experts, you will ground the design in a deep understanding of how the harm occurs and translate that understanding into a system of defence. You will connect detection with policy, review, interventions, enforcement and measurement, continually calibrating the system against real cases and expert judgement as it scales.
You will identify what needs to be built or changed and make it happen. Success requires setting clear priorities, aligning partners, resolving dependencies and communicating evidence, decisions and trade-offs crisply. It also requires a willingness to jump in and work directly on whatever is blocking system effectiveness, using your breadth of skills.
This role is based in our London office and includes 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.
In this role, you will:
- 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 risks within your area of focus. For scams, identify patterns of deception, impersonation and coordinated victim targeting, and translate those findings into detection criteria. For suicide and self-harm, work with domain experts to identify harmful interactions and distinguish them from supportive conversations, help-seeking and legitimate discussion.
- Build context-sensitive protections. Partner with Policy and Operations to develop review criteria, escalation pathways and interventions suited to the harm. Evaluate both missed harms and false positives, using expert judgement and operational feedback to improve the system.
- 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. Use expert feedback and operational outcomes to guide improvements.
- 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.
You might thrive in this role if you:
- Think in systems. You have enough breadth across technical, analytical, investigative and operational disciplines to understand how they fit together, recognise gaps and translate between specialist perspectives.
- Bring deep expertise in scams, fraud, suicide and self-harm, jailbreaks, or a closely related harm domain. Relevant backgrounds may include fraud detection, trust and safety investigations, online safety, adversarial testing of AI safeguards, or technical work on protections for vulnerable users. You do not need expertise across all of these areas.
- Can translate domain judgement into reliable detection and review criteria. For scams, this may mean recognising evolving deception and actor behaviour; for suicide and self-harm, it may mean evaluating conversational context and reasoning carefully about harmful, supportive and ambiguous interactions.
- Are proficient in SQL and Python and have experience writing reliable and efficient production code for detection and data processing. Additional ML or SWE experience is a plus.
- Can apply quantitative analysis and machine-learning methods to measure risks and evaluate system effectiveness. You understand the limitations of your data and can reason about missed harms, false positives and appropriate interventions. Additional DS/measurement background is a plus.
- Have experience setting strategy and delivering complex, cross-functional technical projects. You can turn an ambiguous problem into a plan, align people with different priorities and drive work through to completion.
- Communicate clearly and concisely in writing and conversation. You can explain technical findings, make actionable recommendations and surface uncertainty and trade-offs to different audiences.
- Can use language models and other automation to scale analytical, investigative or operational work, with evaluation and human oversight appropriate to the problem.
About OpenAI
OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity.
OpenAI's standard text
We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.
For additional information, please see OpenAI’s Affirmative Action and Equal Employment Opportunity Policy Statement.
Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates. For unincorporated Los Angeles County workers: we reasonably believe that criminal history may have a direct, adverse and negative relationship with the following job duties, potentially resulting in the withdrawal of a conditional offer of employment: protect computer hardware entrusted to you from theft, loss or damage; return all computer hardware in your possession (including the data contained therein) upon termination of employment or end of assignment; and maintain the confidentiality of proprietary, confidential, and non-public information. In addition, job duties require access to secure and protected information technology systems and related data security obligations.
To notify OpenAI that you believe this job posting is non-compliant, please submit a report through this form. No response will be provided to inquiries unrelated to job posting compliance.
We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via this link.
OpenAI Global Applicant Privacy Policy
At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.
What this role asks for
Standard for software engineering roles
Python
Common in software engineering postings at any company.
78% of this description is written for the role. The rest is OpenAI's standard text, folded away below.
Compared with OpenAI's other open jobs.
The team: Applied AI Engineering HIRES STEADILY
This role is one of 68 open in Applied AI Engineering. 12 were posted in the last 30 days and the oldest in September: a team that hires all year rather than one being built.
WHAT THE TEAM WORKS WITH, ACROSS ITS POSTINGS
Python (16 of 68), Machine Learning (11 of 68), LLM (7 of 68), React (7 of 68), TypeScript (7 of 68), Golang (6 of 68), Android (5 of 68)
OTHER ROLES ON THIS TEAM
- Software Engineer, Agent Identity posted Nov 18
- Full Stack Software Engineer, Dots for Companies posted Nov 17
- Software Engineer, Presence posted Nov 17
- Data Engineering Manager, Devices posted Nov 16
- Engineering Manager, Education posted Nov 12
- Android Engineer, Growth posted Nov 10
- Software Engineer, Guardian posted Nov 5
- Staff Backend Engineer, Financial Engineering posted Nov 4
- Engineering Manager, API Multicloud posted Nov 3
- Engineering Manager, Guardian posted Oct 28
- Full Stack Software Engineer, Monetization Platform posted Oct 23
- Principal Software Engineer, ChatGPT Education and Learning posted Oct 23
- Software Engineer, Backend — Dots posted Oct 19
- Software Engineer, Full Stack — Dots posted Oct 16
- Software Engineer, Mobile Web — Dots posted Oct 16
- Machine Learning Engineer, Implicit Signals posted Oct 13
- Data Engineer, Core Experimentation posted Oct 6
- Software Engineer, Shop/Feed Ads posted Oct 6
- Android Engineer, Plugin Developer Platform posted Oct 5
- Frontend Software Engineer, Codex App posted Oct 1
- Engineering Manager, ChatGPT Space posted Oct 1
- Software Engineer, Implicit Signals posted Sep 29
- Software Engineer, Product Velocity posted Sep 28
- Software Engineer, Search Infrastructure posted Sep 25
- Machine Learning Engineer, Core Experimentation posted Sep 24
- Staff & Software Engineer, Payments & Billing, Consumer Monetization posted Sep 24
- Mobile / Full Stack Staff & Software Engineer, Consumer Monetization posted Sep 24
- Full Stack Staff & Software Engineer, Consumer Monetization posted Sep 24
- Product Manager, Technology Vertical posted Sep 23
- Machine Learning Engineer, Monetization AI/ML posted Sep 21
- Software Engineer, Plugin Ecosystem posted Sep 21
- Data Engineering Manager, Growth & Revenue posted Sep 14
- Software Engineer, Ads Integrity posted Sep 14
- Android Engineer, ChatGPT Library Team posted Sep 9
- Full Stack Software Engineer, Product Explorations posted Sep 3
- Software Engineer, Financial Engineering posted Aug 28
- Software Engineer, Plugin Developer Platform posted Aug 18
- Software Engineer, Model Deployment- ChatGPT Engineering posted Aug 17
- Senior Staff Software Engineer, Identity posted Aug 6
- Product Evals Engineer, ChatGPT Learning posted Aug 4
- Software Engineer, Enterprise Verticals posted Jul 29
- Software Engineer, ChatGPT Shopping posted Jul 9
- Engineering Manager, MLE posted Jun 23
- Full Stack Software Engineer, ChatGPT ImageGen posted Jun 9
- Software Engineer, Scaled Abuse posted Jun 8
- Software Engineer, Monetization ML Infrastructure posted Jun 1
- Software Engineer, Ads Manager posted May 26
- Software Engineer, Ad Formats posted May 26
- Engineering Manager, Distillation & Detection Platform posted May 20
- Software Engineer, Identity Platform posted May 14
- Full-Stack Software Engineer, Applied Foundations posted May 7
- Backend Software Engineer, Applied Foundations posted May 7
- Software Engineer, ChatGPT Infrastructure posted Apr 21
- Full Stack Software Engineer, Education posted Apr 16
- ChatGPT Performance Engineer posted Apr 15
- Software Engineer, Localization posted Mar 18
- Software Engineer, Infrastructure - Core Experimentation posted Mar 17
- Software Engineer, Full-Stack - Core Experimentation posted Mar 17
- Full Stack Software Engineer, Growth posted Jan 30
- iOS Engineer, Applied Foundations posted Jan 20
- Android Engineer, Applied Foundations posted Jan 20
- Software Engineer, Monetization Product & Platform posted Jan 8
- Software Engineer, Monetization Delivery posted Dec 10
- Software Engineer, Habitat (Online Data) posted Apr 14
- Software Engineer, Youth Well-Being posted Nov 22
- Software Engineer, Integrity Foundations posted Jun 11
- Data Engineer posted Sep 26
From the team and dates on OpenAI's own job board.
Similar jobs
- Data Engineer at UBDS Group
Shares 4 skills: Cybersecurity, Machine Learning, SQL… · same seniority · same city - Software Engineer - Red Team at AI Security Institute
Shares 3 skills: Cybersecurity, Machine Learning, Python · same seniority · same city - Data Scientist - Algorithm Researcher at Dawn Security Inc.
Shares 2 skills: Cybersecurity, Python · same seniority - Azure Engineer at Sword Group
Shares 2 skills: Cybersecurity, SQL · same seniority · same country - Senior Data Scientist at Gen Digital
Shares 4 skills: Cybersecurity, Machine Learning, SQL… - Software Engineer, Agent Identity at OpenAI
Also at this company
More jobs like this
Is this your posting? Email [email protected] to have it removed.