Researcher, Safety Training

OpenAI

Where
San Francisco

Posted 42 months ago· Checked live at OpenAI 1 hour ago

Stale: open 1274 daysUp for more than two weeks. It may already be filled.

See how you score for this job

One sentence and your resume. We score it against what OpenAI asks for, line by line.

See my score
Is this job still open?
Yes. We checked it live on OpenAI's own hiring page 1 hour ago.
What is the job?
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.
What does it pay?
The posting doesn't say.
Our verdict
Stale. Up for more than two weeks. It may already be filled.

What the job is

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.

In this role, you will

  • Conduct research on safety post-training methods, including RLHF, RLAIF, DPO, PPO, reward modeling, adversarial training, synthetic data, and scalable oversight
  • Develop and implement model training interventions that make models safer, more reliable, and more aligned with user intent
  • Build evaluations and measurement infrastructure for safety harms, high-stakes reliability failures, policy adherence, jailbreak robustness, multimodal risks, agent behavior, and domain-specific risks
  • Translate ambiguous safety problems into concrete research plans, datasets, training runs, evals, and product-facing improvements
  • Analyze model failures such as hallucination, unsafe tool use, prompt injection, privacy leakage, over-refusal, under-refusal, sycophancy, and deceptive or misleading behavior
  • Partner with domain experts to design safety training approaches for areas like cyber, privacy, youth safety, wellbeing, and other frontier-risk domains
  • Collaborate with research and deployment teams to ensure safety improvements are incorporated into OpenAI’s core model training and product launches

You might thrive in this role if you

  • Have hands-on experience training, fine-tuning, or post-training language models, multimodal models, or agentic systems
  • Have experience with RL, RLHF, RLAIF, DPO, PPO, reward modeling, preference optimization, instruction tuning, or related post-training methods
  • Care deeply about shaping model behavior in real-world systems, not only publishing research
  • Are excited by open-ended safety problems where the right method, dataset, eval, or training objective may not be obvious at the start
  • Bring strong research judgment and strong engineering ability, including comfort running experiments, analyzing model behavior, and working with large-scale ML systems
  • Have experience in one or more relevant domains: agents, tool use, multimodal models, cyber/security, reliability, uncertainty calibration, factuality, evals, privacy, youth safety, wellbeing, or applied alignment
  • Enjoy collaborating across research, engineering, product, policy, legal, and trust and safety teams
  • Hold a PhD in machine learning, computer science, or a related field, or have equivalent practical research or engineering experience

Nice to have

  • Experience improving production model behavior through post-training or deployment feedback
  • Experience building safety evals, automated graders, red-teaming systems, or monitoring pipelines
  • Experience working with human feedback, expert feedback, synthetic data, or policy-grounded training data
  • Experience in safety-critical or abuse-sensitive domains where models must balance helpfulness, refusal, uncertainty, and user intent

Similar open jobs

Jobs in San Francisco (11750)Jobs in London (726)