Researcher, Safety Oversight

About the Team The Agent Safety team works to ensure that increasingly capable AI agents act safely, exercise sound judgment, and remain aligned with user intent. Our mission is to reduce the probability of severe unintended outcomes from increasingly capable AI agents while preserving their ability to act effectively and autonomously. Our work spans three areas: Training: Create training methods, environments and data that teach agents to make better decisions in consequential situations. We turn real-world failures into training signals that prevent similar incidents, and identify precursor behaviors and mitigations to address emerging risks. Measurements: Build evaluations and production metrics that identify emerging risks and measure whether our interventions work. Oversight : Develop oversight and system mitigation mechanisms that reduce harmful actions while preserving useful agent autonomy (for example future versions of auto-review ). About the Role This role focuses on oversight and system-level mitigations that enable increasingly capable agents to operate safely and autonomously in real environments. We prioritize building oversight systems that are used in practice today, both internally and externally (see our recent work on action monitoring for codex and former code review ). We also study longer-term questions about how increasingly capable agentis systems can be supervised, constrained, and corrected. We’re looking for a safety&security minded researcher or engineer who can reason rigorously about security boundaries and agent behavior, then build and test practical mitigations. A background in AI control or security is welcome but not required. This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees. In this role, you will: Design, build, and evaluate system-level controls for agent actions like agent-based review. Plan how they fit in a broader syste

About the Team The Agent Safety team works to ensure that increasingly capable AI agents act safely, exercise sound judgment, and remain aligned with user intent. Our mission is to reduce the probability of severe unintended outcomes from increasingly capable AI agents while preserving their ability to act effectively and autonomously. Our work spans three areas: Training: Create training methods, environments and data that teach agents to make better decisions in consequential situations. We turn real-world failures into training signals that prevent similar incidents, and identify precursor behaviors and mitigations to address emerging risks. Measurements: Build evaluations and production metrics that identify emerging risks and measure whether our interventions work. Oversight: Develop oversight and system mitigation mechanisms that reduce harmful actions while preserving useful autonomy (for example future versions of auto-review ). About the Role We’re looking for strong executors with excellent judgment, comfort with ambiguity, and an understanding of frontier model research. You don’t need prior safety or alignment experience, we also welcome people that recently realized that alignment and safety is a critical area to contribute to. This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees. In this role, you will: Train and evaluate frontier models to reduce harmful or misaligned agent actions, forming clear hypotheses and executing independently through ambiguity. Mine incidents and build scalable measurement, data-processing, and evaluation systems that turn real failures into repeatable safety signals. Collaborate closely with post-training, capabilities, oversight, and pre-training partners to ship research-backed mitigations into large-scale training and agent systems. You might thrive in this role if you: Have demonstrated strength in research engineering, ML en

About the team Models are becoming increasingly capable—moving from tools that assist humans to agents that can plan, execute, and adapt in the real world. Mitigating the frontier risks resulting from these capabilities is paramount to OpenAI’s ability to continue deploying models safely. The Preparedness team is dedicated to addressing these critical risks. Our work includes: Measurement. Monitoring and predicting the evolving capabilities of frontier AI systems. Mitigation. Keeping misalignment safeguards, alignment tools, and on track to adequately address extreme threats that might arise in the future. Coordination. Setting mitigation targets by maintaining OpenAI’s preparedness framework , and partnering with other staff to achieve these targets. This is urgent, fast-paced work that has far-reaching implications for the company and for society. About the role Preparedness is hiring strong technical executors to support preparations for accelerated AI development, which may culminate in recursive self-improvement. This work relies on anticipating misalignment risks that might exist in the future, but might not exist now; so it’s especially important that people in this role are tasteful and strategic. The role is wide-ranging, covering any mitigation for loss of control risk, spanning the design and implementation of better pre-deployment risk-assessment , control measures , RSI-relevant training interventions, and turning one’s technical work into established institutional practices and external-facing communications. Below is a subset of our focus areas: Scalable oversight: Establishing practices for model misbehavior monitoring and oversight which remain effective in superhuman model capability regimes, with a focus on bridging from today’s monitoring approaches to future-proof ones. Automated auditing: As model capabilities increase, we’ll increasingly rely on automated approaches for finding the most severe forms of model misalignments. We’ll both need to s

About the Team The CoT Monitorability team at OpenAI studies whether and when the chain-of-thought of frontier reasoning models is monitorable enough to support scalable oversight. We study how to measure monitorability , which training mechanisms affect monitorability, and speculative methods to improve monitorability. While we mostly focus on CoT monitorability at the moment, we care more generally about any form of monitorability, auditing methods, and improving alignment. We were the first to show that chain-of-thought monitoring can be a practical additional safety mechanism, and today our monitoring systems are actively used on OpenAI’s largest RL training runs to detect misbehavior. The issues we surface are then used to help improve our reward functions, environments, etc (without directly training against a CoT monitor). Our work sits in Alignment and intersects with model training, alignment evaluations, monitoring, and frontier-risk research.We care most about monitorability where the stakes are high, and about preserving useful oversight signals as models become more capable. About the Role We’re looking for a researcher with strong empirical ML expertise and a deep interest in model behavior, alignment, or interpretability. Direct chain-of-thought interpretability experience is welcome but not required; strong candidates may come from broader interpretability, alignment, model training, or investigative model-behavior work. As a researcher on the Alignment team, you will design and run experiments that improve our understanding of model monitorability. You will investigate how training interventions across the model-development pipeline influence whether reasoning remains legible, build evaluations that make those questions measurable, and help translate findings into practical oversight and training recommendations. You may also help develop new monitoring models or methods and apply them to OpenAI’s largest training runs. This role is especially well

About the Team OpenAI’s People team hires, engages, and retains world-class talent to safely build and deploy AGI that benefits all of humanity. The People Analytics team helps leaders make rigorous, evidence-based talent decisions and ensures that the systems supporting those decisions are valid, reliable, fair, and accountable. About the Role As a People Data Scientist focused on AI fairness and bias testing, you will help establish how OpenAI evaluates AI-assisted People systems and high-impact talent processes. You will design and conduct rigorous assessments to identify, measure, and mitigate potential bias across the lifecycle of models, agents, decision-support tools, and automated workflows. Your work will span the entire employee life-cycle, such as hiring, performance, promotion, employee development, workforce planning, etc. You will evaluate both technical systems and the broader human-AI decision processes in which they operate, examining not only model performance but also data quality, measurement validity, differential outcomes, human oversight, and unintended consequences. We’re looking for an experienced data scientist or applied researcher who can translate complex fairness questions into defensible evaluation strategies, scalable testing infrastructure, and clear recommendations for technical teams and senior leaders. This role is preferred to be based in San Francisco, CA. In this role, you will: Define and lead fairness and bias-testing strategies for AI-assisted People processes, models, agents, and decision-support systems from development through deployment and ongoing monitoring. Design rigorous algorithmic audits and validation studies, including adverse-impact analysis, subgroup and intersectional evaluation, error-rate analysis, calibration, measurement invariance, reliability, criterion-related validity, and sensitivity testing. Identify the appropriate fairness criteria for each use case, evaluate tradeoffs among competing definitions

About the Team OpenAI’s Governance team helps shape how the company responsibly develops and deploys increasingly capable AI. We bring together technical evidence, policy, and operational perspectives to help the company address emerging risks, resolve difficult questions, and make well-supported decisions. Our work includes shaping and improving governance practices, supporting effective oversight, developing clear assessments and recommendations, and ensuring that decisions lead to action. We work closely with research, safety, security, legal, and product teams to identify gaps, reconcile different views, and improve our approach as capabilities and circumstances change. About the Role We are looking for a curious, high-agency Research Program Manager who can reason from first principles, make sense of incomplete or conflicting information, and move difficult work forward. You will help shape the substance of governance reviews, connect ideas and evidence across teams, and develop recommendations that are both well-founded and practical. The work requires someone who can use established approaches where they fit, recognize when circumstances call for a different approach, and update their thinking as new evidence emerges. You should bring sound judgment, a willingness to experiment and learn, and the program-management discipline to turn good analysis into action. Depending on your experience and the team’s needs, your work may focus on safety advisory and board-level oversight, deployment governance, or standards and strategic partner commitments. In this role, you will: Bring together technical, policy, and operational inputs to develop coherent assessments, recommendations, and decision materials for governance bodies and senior leaders. Work through emerging or ambiguous questions, test assumptions, identify gaps or conflicting evidence, and help determine what additional analysis or decisions are needed. Engage critically with research, evaluations, safeguar