Researcher, Loss of Control

Details

About the team

The Safety Systems org ensures that OpenAI’s most capable models can be responsibly developed and deployed. The Preparedness team within Safety Systems is guided by OpenAI’s Preparedness Framework and focuses on identifying, tracking, and preparing for catastrophic risks related to frontier AI models. The team connects capability assessment, evaluations, internal red teaming, and mitigations for frontier models, and coordinates on AGI preparedness.

About the role

As frontier AI systems become more capable, they can pursue long-horizon goals, use tools, adapt to feedback, and operate with greater autonomy. These advances introduce risks that models may be misaligned, deceptive, or difficult to supervise or contain. As a Researcher for loss of control mitigations, you will design and implement an end-to-end mitigation stack to reduce the risk of intentionally subversive or insufficiently controllable model behavior across OpenAI’s products and internal deployments. This role requires strong technical depth and close cross-functional collaboration to ensure safeguards are enforceable, scalable, and effective.

Responsibilities

• Design and implement mitigation components for loss of control risk spanning prevention, monitoring, detection, containment, and enforcement under guidance from senior technical and risk leadership.
• Integrate safeguards across product and research surfaces in partnership with product, engineering, and research teams to ensure protections are consistent, low-latency, and resilient as usage and model autonomy increase.
• Evaluate technical trade-offs within the loss of control domain (coverage, robustness, latency, model utility, and operational complexity) and propose pragmatic, testable solutions.
• Collaborate with risk modeling, evaluations, and policy partners to align mitigation design with anticipated failure modes and high-severity threat scenarios, including deceptive alignment, hidden subgoals, reward hacking, and attempts to evade oversight.
• Execute rigorous testing and red-teaming workflows to stress-test the mitigation stack against increasingly capable and potentially subversive model behaviors (e.g., sandbagging, monitor evasion, exploit-seeking, unsafe tool use, strategic deception) and iterate based on findings.

Requirements

• Passion for AI safety and motivation to make cutting-edge AI models safer for real-world use.
• Demonstrated experience in deep learning and transformer models.
• Proficiency with frameworks such as PyTorch or TensorFlow.
• Strong foundation in data structures, algorithms, and software engineering principles.
• Familiarity with methods for training and fine-tuning large language models, including distillation, supervised fine-tuning, and policy optimization.
• Ability to work collaboratively with cross-functional teams across research, policy, product, and engineering.
• Significant experience designing and evaluating technical safeguards, control mechanisms, or monitoring systems for advanced AI behavior.
• (Nice to have) Background knowledge in alignment, control, interpretability, robustness, adversarial ML, or related fields.

Benefits

• Base pay range listed above; total compensation may also include equity and performance-related bonus(es) for eligible employees.
• Medical, dental, and vision insurance with employer contributions to Health Savings Accounts.
• Pre-tax accounts (Health FSA, Dependent Care FSA, commuter accounts).
• 401(k) retirement plan with employer match.
• Paid parental, medical, and caregiver leave.
• Paid time off (flexible PTO for exempt employees; up to 15 days annually for non-exempt employees).
• 13+ paid company holidays and coordinated office closures, plus paid sick or safe time as required by law.
• Mental health and wellness support; employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily meals in offices and meal delivery credits as eligible.
• Relocation support for eligible employees.
• Additional taxable fringe benefits (charitable donation matching, wellness stipends) as applicable.

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. OpenAI is an equal opportunity employer and provides reasonable accommodations to applicants with disabilities. Background checks for applicants will be administered in accordance with applicable law for US-based candidates.