Research Engineer / Research Scientist, RL and Reasoning at OpenAI (San Francisco)
Job Description
OpenAI’s RL and Reasoning team, which developed the o1 and o3 reasoning models, is hiring research engineers and scientists in reinforcement learning. The team pushes RL research, builds next-generation generative models and deploys them at scale. The ad looks for people with an RL research background who iterate quickly and code well.
At a glance
- Team: RL and Reasoning
- Location: San Francisco, hybrid (3 days a week in the office), relocation offered
- Pay: $295,000 – $445,000 a year plus equity, as listed
- Apply: open until filled (re-checked 14 October 2026)
What you would do
- Advance AI alignment and capabilities with reinforcement learning methods
- Help train intelligent, aligned, general-purpose agents and the systems behind OpenAI’s models
- Run simple, tightly controlled experiments and reach conclusions that hold up
- Dive into a large ML codebase to debug and improve it
Why this role matters
Reasoning models such as o1 and o3 learned to think step by step through reinforcement learning, which moved RL from games and robotics into the centre of language-model research. This team works at that frontier, so the role offers first-hand work on some of the most capable models in use and on the methods that train them.
What OpenAI is looking for
- A background in reinforcement learning research
- Strong coding skills and the ability to iterate quickly
- A deep understanding of machine learning and its applications
- Comfort in a fast-moving, technically complex environment
Nice to have
- Experience with language-model research
Pay and location
OpenAI lists $295,000 to $445,000 a year plus equity. The role is hybrid (three office days a week) and relocation help is offered.
How to apply
Apply through the official OpenAI job posting. OpenAI’s posting does not give a closing date, so the role is open until filled; ResearchJobs.in will re-check this listing on 14 October 2026. Check the posting for location and work-authorisation details before you apply.
See all our artificial intelligence jobs, or browse more research jobs on ResearchJobs.in.
Hiring institution: OpenAI
Official advertisement: jobs.ashbyhq.com
How to prepare for this application
- Lead with RL: papers, open-source work or projects in reinforcement learning.
- Show rigour: the team values principled experiments over flashy results.
- Codebase skills: give examples of debugging or improving large ML systems.
- Language models: RL applied to LLMs (RLHF, RL from verifiable rewards) is directly relevant.
About OpenAI
OpenAI is an AI research and deployment company behind the GPT and o-series models, ChatGPT, Codex and the OpenAI API. Its research teams work on training, reasoning, alignment, safety and evaluation of frontier models, mostly from San Francisco.
