Job Description
OpenAI’s Safety Systems organisation is hiring a senior researcher for its Model Safety Research team, which works out how to make models behave safely and robustly without losing helpfulness. The researcher sets research directions and runs projects on topics such as RLHF, adversarial training and robustness, and ships safety improvements into OpenAI’s models and products.
At a glance
- Team: Safety Systems – Model Safety Research
- Location: San Francisco
- Pay: $380,000 – $500,000 a year plus equity, as listed
- Apply: open until filled (re-checked 14 October 2026)
What you would do
- Carry out leading research on AI safety topics such as RLHF, adversarial training and robustness
- Implement new methods in OpenAI’s core model training and launch safety improvements in products
- Set research directions for safer, more aligned and more robust models
- Work on enforcing nuanced safety policies, adversarial robustness and privacy and security risks
Why this role matters
Making a model refuse harmful requests without becoming unhelpful, and keeping it robust to people trying to break it, are central problems for any lab that deploys AI widely. This senior role shapes how OpenAI approaches them, and the methods developed here go straight into the training of production models.
What OpenAI is looking for
- Substantial experience in AI safety research
- Strong machine learning research and engineering skills
- Ability to set and lead research directions
Nice to have
- Experience deploying safety methods in production models
Pay and location
OpenAI lists $380,000 to $500,000 a year plus equity for this senior San Francisco role.
How to apply
Apply through the official OpenAI job posting. OpenAI’s posting does not give a closing date, so the role is open until filled; ResearchJobs.in will re-check this listing on 14 October 2026. Check the posting for location and work-authorisation details before you apply.
See all our artificial intelligence jobs, or browse more research jobs on ResearchJobs.in.
Hiring institution: OpenAI
Official advertisement: jobs.ashbyhq.com
How to prepare for this application
- Senior means direction-setting: show research agendas you shaped.
- Robustness work: adversarial training or red-teaming results are directly relevant.
- Production impact: safety methods you shipped into real models carry weight.
- Helpfulness trade-offs: be ready to discuss safety without over-refusal.
About OpenAI
OpenAI is an AI research and deployment company behind the GPT and o-series models, ChatGPT, Codex and the OpenAI API. Its research teams work on training, reasoning, alignment, safety and evaluation of frontier models, mostly from San Francisco.