Job Description
OpenAI’s Privacy Engineering team is hiring a research engineer in privacy-preserving machine learning. The work applies research on differential privacy, federated learning and data memorisation to OpenAI’s systems, and defends models against privacy attacks such as membership inference and model inversion while keeping them useful.
At a glance
- Team: Privacy Engineering
- Location: San Francisco, relocation available
- Pay: Listed in the posting
- Apply: open until filled (re-checked 14 October 2026)
What you would do
- Design and prototype privacy-preserving ML algorithms such as differential privacy, secure aggregation and federated learning at OpenAI scale
- Measure and strengthen models against membership inference, model inversion and memorisation leaks, balancing utility with provable guarantees
- Build internal libraries, evaluation suites and documentation that make privacy techniques easy for other teams to use
- Lead in-depth investigations into how privacy and machine learning interact
Why this role matters
Large models can memorise and leak parts of their training data, so privacy has become a research problem as well as a policy one. Differential privacy and federated learning give formal protections, but making them work at the scale of frontier models is still open research. This role sits where that research meets products used by hundreds of millions of people.
What OpenAI is looking for
- Research or engineering experience in privacy-enhancing technologies
- Strong machine learning and software engineering skills
- Understanding of privacy attacks on models and how to measure them
Nice to have
- Publications in differential privacy or ML privacy
Pay and location
OpenAI publishes a pay range for this role on the posting; please check it there. The role is in San Francisco and relocation is available.
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
- Differential privacy: show projects with formal guarantees, not just anonymisation.
- Attacks: experience running membership-inference or extraction attacks is valuable.
- Tools: libraries or evaluation suites you built for others help your case.
- Scale: explain how your methods would work on very large models.
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.