Senior Researcher — Safety Systems, Misalignment Research

Details

About the team

Safety Systems sits at the forefront of OpenAI’s mission to build and deploy safe AGI, ensuring the most capable models can be released responsibly and for the benefit of society. The Misalignment Research taskforce focuses on identifying, quantifying, and understanding future AGI misalignment risks well in advance of when they can pose harm.

The work of this research taskforce spans four pillars:

• Worst-Case Demonstrations — Craft compelling, reality-anchored demos that reveal how AI systems can go wrong, with a focus on high-importance cases where misaligned AGI could pursue goals at odds with human well-being.
• Adversarial & Frontier Safety Evaluations — Transform demos into rigorous, repeatable evaluations that measure dangerous capabilities and residual risks (topics include deceptive behavior, scheming, reward hacking, deception in reasoning, power-seeking, and related areas).
• System-Level Stress Testing — Build automated infrastructure to probe entire product stacks and assess end-to-end robustness under extreme conditions, escalating tests until breaking points are found as systems improve.
• Alignment Stress-Testing Research — Investigate why mitigations break and publish insights that shape strategy and next-generation safeguards; collaborate with other labs and share misalignment findings.

About the role

We are seeking a Senior Researcher passionate about red-teaming and AI safety. In this role you will design and execute cutting-edge attacks, build adversarial evaluations, and advance our understanding of how safety measures can fail and how to fix them. Your insights will directly influence OpenAI’s product launches and long-term safety roadmap. The role is hybrid (New York City).

Responsibilities

• Design and implement worst-case demonstrations that make AGI alignment risks concrete for stakeholders, focusing on high-stakes use cases.
• Develop adversarial and system-level evaluations grounded in those demonstrations and drive adoption across OpenAI.
• Create automated tools and infrastructure to scale automated red-teaming and stress testing.
• Conduct research on failure modes of alignment techniques and propose improvements.
• Publish influential internal or external papers that shift safety strategy or industry practice.
• Partner with engineering, research, policy, and legal teams to integrate findings into product safeguards and governance processes.
• Mentor engineers and researchers, fostering a culture of rigorous, impact-oriented safety work.

Requirements

• 4+ years of experience in AI red-teaming, security research, adversarial ML, or related safety fields.
• Strong research track record (publications, open-source projects, or high-impact internal work) demonstrating creativity in uncovering and exploiting system weaknesses.
• Fluency in modern ML/AI techniques and comfort hacking on large-scale codebases and evaluation infrastructure.
• Experience designing adversarial evaluations, system-level stress tests, or automated red-teaming infrastructure.
• Ability to communicate clearly with technical and non-technical audiences and translate complex findings into actionable recommendations.
• Collaborative mindset; ability to drive cross-functional projects spanning research, engineering, policy, and legal teams.
• Ph.D., master’s degree, or equivalent experience in computer science, machine learning, security, or a related discipline (nice to have but not required).

Benefits

• Competitive compensation (base range listed), equity, and benefits.
• Access to cutting-edge models, tooling, and compute resources.
• A highly collaborative, mission-driven environment with world-class colleagues.
• Medical, dental, and vision insurance with employer HSA contributions; pre-tax FSA options; 401(k) with employer match.
• Paid parental leave and other paid leave policies; flexible PTO for exempt employees.
• 13+ paid company holidays and multiple company office closures throughout the year.
• 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 notes

• Background checks will be administered in accordance with applicable law for U.S.-based candidates; qualified applicants with arrest or conviction records will be considered consistent with applicable laws.
• OpenAI is an equal opportunity employer and provides reasonable accommodations to applicants with disabilities.