TLDR;
We’re hiring Research Engineers and Research Scientists to work on Ambitious Mechanistic Interpretability (AMI) at Principles of Intelligence: designing novel tools to reverse engineer current-day systems (such as innovating on SAEs and weight-based decompositions), exploring how interpretability tools can be used during training for better safety guarantees, and researching interpretable architectures by design. Fully remote. Strong motivation to work in AI Safety required. Apply here by 31 March, 2026.
Position Details
- Location: Remote. Strong preference for candidates based in or able to spend significant time in London (UK) and/or the Bay Area (US).
- Visa / Work authorization: We can provide visa sponsorship for candidates based in (or relocating to) London (UK) and Berkeley / Bay Area (US), depending on candidate circumstances and role fit.
- Type: Full-time.
- Start date: May 2026.
- Salary range: Salary is dependent upon location and experience. Our estimated range for research engineers is $60,000–$180,000 gross and for research scientists is $80,000–$250,000 gross.
- Deadline to apply: Please submit the application form by 31 March 2026. Applications will be reviewed on a rolling basis.
- Referrals: We’re happy to receive referrals. Please submit recommended candidates via this form.
Core Responsibilities
We are hiring for a Research Engineer & Research Scientist to work on Ambitious Mechanistic Interpretability at PrincInt. The work is aimed at building and advancing methods to:
- Develop new unsupervised training methods used to reverse engineer current-day systems (i.e. SAEs, Weight Based Decomposition Methods)
- Explore training-time uses of interpretability tools for better safety guarantees
- Design new neural network architectures which are interpretable by design
This role is fully remote, so we’re looking for people who can thrive in an async environment and are genuinely excited to work on AI safety.
Requirements
We care most about whether you can contribute strongly to AMI work and collaborate effectively in a fully remote environment. Strong candidates will have many of the following:
Research Engineer
- Salary: $60,000–$180,000 gross (depending on location and experience)
- Must have
- Strong SWE background and working experience with ML
- Experience working with LLMs, i.e. capable of running evaluations
- Comfortable working in a fully remote environment
- Should have
- Familiarity with AI Safety research engineering, i.e. content in the ARENA curriculum, or enough ML experience to quickly pick it up
- Experience with AI assisted programing and tool use
- Great to Have
- Strong mathematical foundations and/or prior research experience (e.g., publishing, open-source research, or shipping novel ML methods); comfortable reasoning from first principles and turning ideas into experiments.
- Experience with GPU programming (i.e. you have a good working model of how memory is managed in a GPU system and can write and read CUDA and Triton kernels)
- Experience with parallel and distributed computing in the context of large language models
Research Scientist
- Salary: $100,000–$250,000 gross (depending on location and experience)
- Must have
- PhD or several years research experience in a technical field such as computer science, math, physics, or economic theory
- Ability to effectively communicate novel methods and solutions to both technical and non-technical audiences.
- Should have:
- A publication record in ML or another quantitative field that demonstrates capacity to bring new ideas to the field. We are most interested in working with people with a publication record in mechanistic Interpretability, but are open to exceptional candidates with strong track records from another field.
- Great to Have
- Experience leading and/or playing a senior role in research projects related to machine learning.
Benefits and Salary
Your starting salary range depends on role, prior experience, and location. Our estimated ranges are $60,000–$180,000 for Research Engineers and $100,000–$250,000 for Research Scientists (gross).
Our benefits include:
- Time off: 4 weeks of paid holiday per year, plus additional personal time off.
- Flexible working hours: Flexible working hours with an emphasis on outcomes and reliable coordination with teammates.
- High ownership & autonomy: A high-trust environment where you’ll own your work end-to-end, with meaningful responsibility and room to improve systems.
- Employment type: We’re open to either full employment or a contractor arrangement, depending on location and candidate preference.
- Team meetups: We get together in person 2-4 times a year for focused work time, great conversations, and the kind of momentum you only get when the whole team is in the same room.
Application Process
- Application: Submit an application by March 31, 2026.
- Screening call: Attend a brief screening call, where you’ll have the chance to ask questions about the role.
- Interview: Attend a remote interview to assess strategic thinking and team fit.
- Work trial: Attend a paid, remote work trial where you’ll spend the day meeting the team and completing strategic assessments.
- Team interviews: Attend one/two additional interviews with the team.
- References: Share references who can comment on your aptitudes. Good references can notably strengthen your application.
Diversity and Inclusion
We’re aware that factors like gender, race, and socioeconomic background can affect people’s willingness to apply for roles for which they meet some but not all the suggested attributes. We’d especially like to encourage people from underrepresented backgrounds to express interest.
There’s no such thing as a “perfect” candidate. If you’re on the fence about applying because you’re unsure whether you’re qualified, we’d encourage you to apply.
If you require any adjustments to the application process, such as accessibility accommodations, additional preparation time, or other, please contact [email protected]. We’re happy to support your needs and adjust the application process.
