Skip to content

OpenAI

San Francisco

Researcher, Cyber Safety Training

Posted 21 Nov

Level
Mid level
Experience
Not stated
Work style
Not stated
Full-time
Pay
$380k to $500k

At a glance

The role in plain English

This role involves researching and developing methods to improve the cyber safety of large AI models at OpenAI. It suits candidates with hands-on experience in machine learning or reinforcement learning, particularly those interested in cybersecurity. Day-to-day work includes designing cyber safety evaluations, collaborating with security researchers, and refining post-training techniques to ensure models are both helpful and safe.

What you'll do

  • Design complex cyber safety evaluations for AI models
  • Research post-training techniques to improve model safety
  • Collaborate with cybersecurity researchers to identify context-sensitive model behaviours
  • Integrate and verify safety improvements in large model training runs
  • Coordinate with cross-functional teams on safety standards

What they're looking for

Essential

  • Hands-on experience training or fine-tuning models
  • Ability to build and debug code for training experiments
  • Practical security judgment from industry, research, or competitions
  • Ability to translate ambiguous cases into concrete model decisions

Nice to have

  • Reinforcement learning experience
  • Collaboration with security teams or capture-the-flag participation

Core skills

  • Machine learning
  • Cybersecurity
  • Post-training
  • Evaluation design
  • Python
  • Model fine-tuning

The shape of the job

Technical depth

5/5

FoundationalHighly technical

Requires hands-on ML, post-training, and cybersecurity expertise

Coding required

4/5

Little to noneHeavy coding

Requires building and debugging code for training experiments

Experience required

3/5

BeginnerExperienced

Requires hands-on ML experience but not senior/lead level

Hands-on focus

4/5

Policy & planningTechnical execution

Focus on designing, building, and testing model training experiments

Cyberend's reading of the listing's duties and requirements, not the employer's own scores.

How the pay compares

Pays more than most similar roles

Pays more than 27 of the 28 open mid level roles in the US on Cyberend that state their pay.

This role
$380k to $500k
Typical similar role
$162k
Difference
$278k more
  • One similar role
  • Where most sit ($146k to $225k)
  • Pay a year, using the middle of each advertised range.

Application toolkit

Make your application count

See which requirements your CV meets and what is missing.

Your CV is used for this answer only and never stored.

Questions to prepare for

  1. 01Describe an experiment where you fine-tuned a model and improved its behaviour.
  2. 02How would you design a cyber safety evaluation for a new AI model?
  3. 03Give an example of a security context where model assistance could cause harm.
  4. 04How do you debug and validate changes in model behaviour after post-training?

About OpenAI

OpenAI is an AI research and deployment company focused on developing and safely deploying advanced AI systems.

Full job descriptionAs published by OpenAI

About the Team

Safety Research at OpenAI is responsible for ensuring our most capable models can be safely deployed in the real world. The Safety Training team develops the research and engineering methods that shape model behavior through post-training, reinforcement learning, evaluation, and deployment feedback.

Our work focuses on making models helpful, reliable, and aligned with safety policies across model types, modalities, and product surfaces. We work across both longer-term safety research and the core post-training work needed to improve production models.

About the Role

You’ll work directly on the large training runs that shape OpenAI’s frontier models. Your focus will be teaching models to help people do legitimate security work while recognizing when their assistance could enable harm. A model that refuses to help a defender investigate a security issue can fail in a different way from one that helps someone misuse it. You’ll study both kinds of mistakes and use what you learn to improve the next training run.

We’re looking for someone with hands-on machine learning experience who wants to bring security judgment into model training. You might come from cybersecurity and want to go deeper on post-training, or from reinforcement learning and want to build substantial expertise in cybersecurity.

In this role, you will

  • Work with cybersecurity researchers to identify situations where context changes what help a model should give.
  • Design complex and realistic cyber safety evaluations.
  • Research post-training techniques that robustly improves the cyber safety of the frontier models.
  • Work with the core post-training team to bring promising methods into large model runs and verify that the safety improvements hold at scale.
  • Coordinate and collaborate with cross-functional teams, including T&S, legal, policy and other research teams, to ensure that our products meet the highest safety standards.

You might thrive in this role if you

  • Have trained or fine-tuned models yourself and can describe an experiment where you used the results to change how you trained the next model.
  • Bring practical security judgment from industry work, a research project, collaboration with a security team, or capture-the-flag competitions. We also welcome reinforcement learning practitioners motivated to develop that judgment alongside security researchers.
  • Can build and debug the code behind a training experiment, from preparing data to checking whether a change in the results reflects a real change in model behavior.
  • Enjoy working through ambiguous cases with domain experts and translating what you learn into concrete decisions about how a model should respond.

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.

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.

  • San Francisco · Remote · $401k to $445k

    Own and build GRC and security systems, including designing data models, integrations, and workflows to support security controls and evidence for audits and compliance. Requires technical product management experience and hands-on implementation skills.

    SeniorData modellingWorkflow automationSecurity controls
    Posted 18 Nov
  • US - Remote · $300k to $340k

    Lead partnerships to design and standardize red-team and purple-team cybersecurity services using AI, enable partner practitioners, and oversee pilots across the Americas. Requires experience in security service delivery and partner management.

    LeadershipRed teamingPurple teamingSecurity testing
    Posted 17 Nov
  • San Francisco; US - Remote · $401k to $510k

    Lead and develop the threat detection and response engineering team, setting technical direction and prioritizing detection work to protect OpenAI’s infrastructure and data. Requires technical leadership and experience managing engineers. US remote or San Francisco.

    LeadershipDetection engineeringIncident investigationAI/ML fluency
    Posted 12 Nov
  • USA - Update Location

    The Information Security Engineer will work on building and maintaining security solutions, likely focused on Zscaler's Zero Trust Exchange platform. Specific daily tasks and required experience are not listed in the job description.

    Mid levelSecurity engineering
    Posted 20 Nov

Hand-picked cyber jobs, every morning.

Cyberend Daily sends a graduate, mid-level, senior and leadership role each day, alongside the security news worth knowing. Free.

Includes our free beginner roadmap · No spam · Unsubscribe anytime