Research Engineer / Research Scientist, Post-Training — Collective Alignment (User Signals)
OpenAI is hiring a Research Engineer / Research Scientist, Post-Training — Collective Alignment (User Signals) in San Francisco, United States. It pays $380k-$500k a year and Level rates it ; you can apply on OpenAI.
Level's read on this job
- Builds AI ●●●● is how Level rates this research scientist role: the job is building AI systems.
- Pay on this posting starts 100% higher than the typical research scientist posting on Level.
- The posting mentions AI safety and AI research among its tools and skills.
- OpenAI has 851 other open roles on Level.
- Posted in the last few days.
AI in this role
About the Team
The Collective Alignment (User Signals) team is a post-training research team working at the intersection of data science, human feedback, and reinforcement learning. We develop methods for learning from real-world user interactions to build AI systems that deliver lasting value, helping people learn, grow, and accomplish increasingly complex goals with ChatGPT.
Learning from user feedback presents fundamental research challenges: signals are often noisy, biased, and difficult to interpret, and improvements in offline metrics do not always translate into better experiences for users. Our team develops scientific approaches to understanding these signals and translating them into improvements in model behavior through evaluations, reward modeling, and post-training.
About the Role
As a Research Engineer or Research Scientist, you will investigate how AI systems can learn from human feedback and real-world usage to better serve users over time.
You will develop new approaches to extracting meaningful learning signals from complex user interactions and incorporating those signals into model training.
This role requires strong deep learning research skills, scientific rigor, and curiosity about how people interact with AI. You will design controlled experiments and ablations, critically examine the relationship between offline evaluations and online model behavior, and work closely with research, product, and data science teams to understand whether improvements translate into meaningful value for users.
In this role, you will:
Develop novel methods for learning from human feedback and user interaction signals.
Research approaches to incorporating feedback into reward modeling, reinforcement learning, and post-training.
Design rigorous experiments and ablation studies to isolate the effects of new data, objectives, and training methods.
Develop offline evaluations and investigate their relationship with online experiments and real-world user outcomes.
Analyze unexpected results, investigate discrepancies between evaluation metrics and user behavior, and develop hypotheses to guide further research.
Evaluate tradeoffs and regressions to improve targeted model behaviors while preserving broader capabilities.
Collaborate with research, alignment, product, and data science teams.
Implement and debug experiments across large-scale deep learning research systems.
You might thrive in this role if you:
Have a strong background in deep learning research through academic or industry experience.
Have demonstrated research ability through publications or substantive research contributions in deep learning or LLM post-training.
Have experience developing new machine learning methods and evaluating them through rigorous, hypothesis-driven experimentation.
Think critically about experimental design, measurement, and what evaluation results do and do not establish about model behavior.
Are comfortable designing ablations, investigating surprising results, and reasoning about the relationship between offline metrics and real-world outcomes.
Have strong programming skills and experience working with complex ML codebases.
Are curious about how people interact with AI and how those interactions can inform better models.
Nice to have:
Experience with RLHF, reinforcement learning, or modern LLM post-training.
Research or demonstrated interest in AI alignment, human feedback, or user signals.
Experience with online experimentation, evaluation methodology, or learning from noisy and biased feedback.
Experience connecting machine learning research with real-world product behavior.
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.
How we rate this
Research Engineer / Research Scientist, Post-Training — Collective Alignment (User Signals) at OpenAI rates 98 out of 100 for how much of the daily work is AI. That makes it Builds AI (AI Level 4 of 4). The level is about AI in the job, not seniority.
Builds AI. The job is building AI systems.
- ●●●● Builds AI80 to 100
- ●●●○ Works on AI60 to 79
- ●●○○ Uses AI40 to 59
- ●○○○ Little AI0 to 39
Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.
Prepare for this job
Built from this posting and from similar jobs on Level.
Skills and AI tools this role asks for
Also common in research scientist jobs at this level
Pay
- This job starts at
- $380k
- Typical research scientist job
- $190k
This posting starts 100% above the typical research scientist job. See research scientist jobs
Questions you could be asked
- How do you think about the risk of an AI system in this kind of role failing silently?
- Tell me about a research question you investigated. What did you find?
- How would you decide a model or AI system is ready to ship?
- Tell me about a time a model underperformed in production. How did you find out, and what did you change?
Adapt your resume
- List these exact terms on your resume: AI Safety and AI Research. An applicant tracking system matches the wording, not the idea.
- Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
- Lead with what you built, trained or shipped. This role is judged on the AI system itself, not the tools around it.
Get new research scientist jobs (Builds AI ●●●●) by email
One email a week, each job rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.
Free.
Similar roles
Research roles that build AI, at other companies.
What kind of AI work fits you?
Answer 12 practical questions in about three minutes. Get a simple profile, the work it points to, and live roles to explore next.
Find my next step