Researcher, Alignment Science

Location

San Francisco

Full time

Research

• $250K – $445K 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.

The Alignment Science team at OpenAI studies the science of intent alignment: how to train models to understand what users are actually asking for, act faithfully on that intent while respecting safety constraints, verify what they did, and report their limitations honestly. Our work sits alongside broader value alignment efforts, but this team focuses on scalable methods for ensuring instruction‑following, honesty, and robustness as models become more capable.

We work on both sides of alignment research: producing externally publishable results and integrating promising techniques into the models OpenAI deploys. Recent team research on model confessions studies how models can be trained to honestly report shortcomings after their original answer, including failures involving hallucination, instruction following, scheming, and reward hacking. That work reflects a broader agenda: build scalable and general methods to ensure models follow human intent.

The team uses a mix of training and evaluation methods, with a focus on reinforcement learning. We care about rigorous, quantitative research that can translate into safer model behavior.

As a Research Engineer / Research Scientist on the Alignment team, you will design and run experiments that help increasingly capable models follow user intent, remain calibrated about correctness and risk, and honestly surface their own mistakes. You will work on hands‑on model training, evaluation design, and research infrastructure, while helping turn promising alignment methods into techniques that can be used in frontier model development.

This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees. We are also open to exceptional remote candidates who can operate independently and collaborate closely with the team.

• Have strong hands‑on experience training, evaluating, or debugging large ML models, especially LLMs.
• Have excellent engineering skills in Python and modern ML frameworks such as PyTorch.
• Bring mathematical rigor, quantitative taste, and comfort turning ambiguous research questions into measurable experiments.
• Have…