Jobs / United States / OpenAI

OpenAI

Research Engineer / Research Scientist, Post-Training — Collective Alignment (User Signals)

San Francisco Posted today

Apply on employer site ↗ Tailor my CV first Source: Company careers site

Optional: we can tailor a CV and cover letter for this job from your real experience first (the first one is free).

Skills this job asks for

TranslationDeep learningLLMsMachine learningA/B testing

Add your CV (free) to see which of these your CV is missing.

Sponsorship verdict

No sponsorship evidence yet

No government record and no wording either way. Not a refusal: ask the recruiter.

  • No government sponsor record hereThis employer posted directly and does not match a government sponsor register.
  • The posting doesn’t mention sponsorshipSilence isn’t a refusal — ask the recruiter before investing much time.
  • No salary bar for this routeH-1B has no fixed salary bar: the employer must pay at least the prevailing wage for the role and area.
  • Confirmed live todayWhen a source last listed this job as open.
Details and sources
No salary bar for this route
H-1B has no fixed salary bar: the employer must pay at least the prevailing wage for the role and area. Cap-subject employers enter a lottery weighted by wage level. Source: https://www.federalregister.gov/documents/2025/12/29/2025-23853/weighted-selection-process-for-registrants-and-petitioners-seeking-to-file-cap-subject-h-1b, rules effective 2026-02-27.

US H-1B: cap-subject employers enter a lottery weighted by wage level — Level I gets 1 entry, Level IV gets 4 (DHS projected selection odds ≈15% at Level I to ≈61% at Level IV). Universities and non-profit research employers are cap-exempt. The $100,000 fee for new petitions from abroad is currently blocked by a court order (appeal pending).

A verdict summarises public evidence. It is not legal advice and never a guarantee: the employer and the immigration authority decide. Sign in to factor in where you can already work.

Before you apply

Sponsorship unknown

No register record and no sponsorship wording in the posting. Worth asking the employer before investing significant time.

These come from the posting’s own wording. Read the original listing to confirm. See better-fit alternatives →

About the 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 ens

Apply on employer site ↗

Join us on Telegram