SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
OpenAI's Applied Foundations team is building a new Integrity Foundations team in London to architect next-generation systems for detecting, tracking, and enforcing against misuse and harm on OpenAI's platforms. This is a 0→1 team opportunity focused on scaled systems that identify and respond to bad actors, financial abuse, and other adversarial threats.
In this role, you will design and build foundational backend and data systems used to detect, track, and enforce against harm using OpenAI's technologies. You'll work closely with technical and non-technical experts in trust and safety, policy, legal, investigations, and harm-specialized engineers to understand emerging harms and inform system design. You'll leverage OpenAI's advanced AI technologies to automate detection and reasoning about complex harms with minimal human intervention, staying ahead of well-resourced adversaries.
You'll collaborate across policy, trust and safety operations, legal, and specialized teams to holistically combat abusive actors. The role requires diving into codebases, building strong intuition for engineering improvements, and staying current with the latest techniques in adversarial defense and harm detection.
Ideal candidates have at least 5 years of backend and data systems engineering experience, plus at least 2 years in trust and safety analysis, investigation, or operations. You're excited to learn from world-class experts on AI-related harms, comfortable with ambiguity and rapid change, and have a strong intrinsic drive to learn and share knowledge. Experience with machine learning techniques is a plus but not required. You should be able to quickly understand complex systems, propose structural improvements, and work effectively in an interdisciplinary environment.
