OpenAI - Researcher, Safety Training

San Francisco, California, United States$380k - $500k+ Equity1w ago

In Office NA Artificial Intelligence Training Specialist Training Development

Requirements

• 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 • 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.

Responsibilities

• 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 • 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

Benefits

• $380K – $500K • Offers Equity • The base pay offered may vary depending on multiple individualized factors, including market location, job-related knowledge, skills, and experience. If the role is non-exempt, overtime pay will be provided consistent with applicable laws. In addition to the salary range listed above, total compensation also includes generous equity, performance-related bonus(es) for eligible employees, and the following benefits. • Medical, dental, and vision insurance for you and your family, with employer contributions to Health Savings Accounts • Pre-tax accounts for Health FSA, Dependent Care FSA, and commuter expenses (parking and transit) • 401(k) retirement plan with employer match • Paid parental leave (up to 24 weeks for birth parents and 20 weeks for non-birthing parents), plus paid medical and caregiver leave (up to 8 weeks) • Paid time off: flexible PTO for exempt employees and up to 15 days annually for non-exempt employees • 13+ paid company holidays, and multiple paid coordinated company office closures throughout the year for focus and recharge, plus paid sick or safe time (1 hour per 30 hours worked, or more, as required by applicable state or local law) • Mental health and wellness support • Employer-paid basic life and disability coverage • Annual learning and development stipend to fuel your professional growth • Daily meals in our offices, and meal delivery credits as eligible • Relocation support for eligible employees • Additional taxable fringe benefits, such as charitable donation matching and wellness stipends, may also be provided. • More details about our benefits are available to candidates during the hiring process. • This role is at-will and OpenAI reserves the right to modify base pay and other compensation components at any time based on individual performance, team or company results, or market conditions. • 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. • We are seeking researchers to advance safety training for OpenAI’s models. You will develop methods that improve model behavior after pretraining, including RLHF, RLAIF, DPO, PPO, preference optimization, adversarial training, synthetic data generation, safety evaluations, and model behavior analysis. • This role is highly cross-functional. You will work with core training teams, product teams, policy, legal, trust and safety, and domain experts to identify risks, design interventions, train models, evaluate outcomes, and launch safety improvements in OpenAI products.