Research Engineer, Language & RL

Save to Kiter
What Openai is looking for in applicants

About the Team

The OpenAI Alignment team fine-tunes large language models to perform tasks in accordance with the user's intentions. We put an emphasis on scalable solutions, and our goal is for increasingly intelligent models to robustly benefit humanity. Our research explores learning from human feedback and decomposing challenging tasks into simpler pieces that are easier to evaluate.

We’re looking for multiple Research Engineers to join the Alignment team. Potential focus areas/projects include:

  • Aligning large language models to follow instructions
  • Training models to find flaws in other models’ outputs
  • Exploring ways to efficiently train from human feedback
  • Training models to assist human feedback

About the Role

As a Research Engineer on the Alignment team, you should be able to:

  • Write performant and clean code for ML training.
  • Independently run and analyze ML experiments to diagnose problems and understand which changes are real improvements.
  • Write clean non-ML code, for example when building interfaces to let workers interact with our models or pipelines for managing human data.
  • Collaborate closely with a small team to balance the need for flexibility and iteration speed in research with the need for stability and reliability in a complex long-lived project.
  • Understand our high-level research roadmap to help plan and prioritize future experiments.

This role may be a good fit for you if you:

  • Want to use your engineering skills to push the frontiers of what state-of-the-art language models can accomplish.
  • Are concerned about risks from misaligned artificial intelligence and want to use your career to help address them.
  • Want to collaborate on open-ended and challenging research questions, building infrastructure and running experiments that have no clear precedent.

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. 

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.

Benefits and Perks
  • Medical, dental, and vision insurance for you and your family
  • Mental health and wellness support
  • 401(k) plan with 4% matching 
  • Unlimited time off and 18+ company holidays per year 
  • Paid parental leave (20 weeks) and family-planning support
  • Annual learning & development stipend ($1,500 per year)
We are an equal opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or other legally protected statuses. Pursuant to the San Francisco Fair Chance Ordinance, we will consider qualified applicants with arrest and conviction records. We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via

Want some tips on how to get an interview at Openai?

What is Openai looking for?
If this role looks interesting to you, a great first step is to understand what excites you about the team, product or mission. Take your time thinking about this and then tell the team! Get in touch and communicate that passion.
What are interviews for Research Engineer like?
Interview processes vary by company, role and team. The best plan is to see what others have experienced and then plan accordingly.
How to land an interview at Research Engineer?
A great first step is organizing your path to an offer. Check out Kiter for tools to get started!