Research Scientist/Engineer (Science of Scheming)

COL Limited; Greater London; On-site; GBP 100,000 - 200,000; Full time

Benefits offered by this job

Market competitive salary

Equity options

Flexible work hours

Unlimited vacation

Provided meals on workdays

Paid work trips

Yearly professional development budget

Job summary

A leading AI research organization in London seeks Research Scientists and Engineers to develop the 'Science of Scheming.' This role involves collaborating with AI developers, studying complex AI dynamics, and creating evaluation techniques. Candidates should possess strong skills in empirical research, analytical reasoning, and software engineering, preferably with experience in training LLMs. The role offers competitive compensation, flexible work hours, and a dynamic work environment.

Qualifications

• Design and execute experiments, striving for speed in iterations.
• Familiar with the problem of AI scheming and existing literature.
• Hands-on experience in training LLMs via reinforcement learning.
• Strong quantitative skills from fields like statistical physics.

Responsibilities

• Collaborate with leading AI developers on various models.
• Study RL dynamics and model organisms to gain insights.
• Develop evaluation techniques for advanced AI models.
• Analyze and extract patterns in reasoning from AI systems.

Skills

Fast-paced empirical research

Conceptual insights about scheming

Software engineering skills

Intense interest in AI progress

Experience RL-training LLMs

Strong analytical skills

Tools

Python

Job description

Application deadline: We are conducting interviews actively and aim to fill this role as soon as we find someone suitable.

ABOUT THE OPPORTUNITY

We want to develop a “Science of Scheming”. The goal is ambitious and we’re looking for Research Scientists and Research Engineers who are excited to build a new hard science from the ground up.

YOU WILL HAVE THE OPPORTUNITY TO

- Collaborate with leading AI developers. We partner with multiple labs, giving you access to a breadth of models that no single AI lab could offer. Through long‑term research collaborations, your work directly impacts how the most capable AI systems are built and deployed.

- Deeply study the RL dynamics that lead to the emergence of reward‑seeking, evaluation awareness or misaligned preferences. Design and train model organisms, and scale your insights to frontier systems.

- Work towards “Scaling laws of scheming”. Build the empirical foundations to predict how scheming risks evolve as models scale in capability.

- Develop novel and ambitious evaluation techniques that have a chance of scaling to highly evaluation aware models.

- Deep dive into AI cognition. Discover patterns in the reasoning processes of frontier AI systems that no one else has ever observed before.

Note: We are not hiring for interpretability roles.

KEY REQUIREMENTS

A diverse range of skill sets will be required to drive our research agenda forward and we don’t expect any single candidate to fulfill all the characteristics below. That being said, a successful candidate likely displays excellence at one or several of the following:

• Fast‑paced empirical research: You can design and execute experiments. You always strive to speed up iteration cycles and relentlessly drive progress towards the next empirical milestone.


• Conceptual insights about scheming: You have deeply thought about the problem of AI scheming and are familiar with all the relevant literature. You are able to turn vague and undefined concepts into concrete and insightful experiment proposals.


• Software engineering skills: Strong software engineering skills correlate highly with effective execution, even in an era of AI agents. Our entire stack uses Python.


• Intense interest in AI progress: You always stay up to date on the latest model releases, and continuously tinker with new and creative AI workflows to speed up your work. You are fascinated by AI cognition and actively spend time trying to understand how they think.


• Experience RL‑training LLMs: You have hands‑on experience in training LLMs via reinforcement learning. You have encountered and resolved countless painful issues from GPU failures to debugging learning instabilities.


• Strong analytical skills: You bring rigorous quantitative chops from working on fields such as scaling laws in LLMs, statistical physics, dynamical systems, applied statistics etc. You’re comfortable building mathematical models of empirical phenomena and know how to extract signal from noisy data.

We want to emphasize that people who feel they don’t fulfil all of these characteristics but think they would be a good fit for the position, nonetheless, are strongly encouraged to apply. We believe that excellent candidates can come from a variety of backgrounds and are excited to give you opportunities to shine. We don’t require a formal background or industry experience and welcome self‑taught candidates.

BENEFITS

• This role offers market competitive salary, equity, and competitive benefits.


• Salary: 100k - 200k GBP (~135k - 270k USD)


• Flexible work hours and schedule


• Unlimited vacation


• Unlimited sick leave


• Lunch, dinner, and snacks are provided for all employees on workdays


• Paid work trips, including staff retreats, business trips, and relevant conferences


• A yearly $1,000 (USD) professional development budget

LOGISTICS

• Time Allocation: Full‑time


• Location: The office is in London, and the building is shared with the London Initiative for Safe AI (LISA) offices. This is an in‑person role. In rare situations, we may consider partially remote arrangements on a case‑by‑case basis.


• Work Visas: We can sponsor UK visas

ABOUT APOLLO RESEARCH

The rapid rise in AI capabilities offers tremendous opportunities, but also presents significant risks. Apollo Research is primarily concerned with risks from Loss of Control, i.e. risks coming from the model itself rather than humans misusing the AI. We’re particularly concerned with deceptive alignment / scheming, a phenomenon where a model appears to be aligned but is, in fact, misaligned and capable of evading human oversight.

We work on the detection of scheming (e.g., building evaluations and novel evaluation techniques), the science of scheming (e.g., model organisms and the study of scaling trends), and scheming mitigations (e.g., control). We closely work with multiple frontier AI companies, e.g., to test their models before deployment and collaborate on fundamental research.

At Apollo, we aim for a culture that emphasizes truth‑seeking, being goal‑oriented, giving and receiving constructive feedback, and being friendly and helpful. If you’re interested in more details about what it’s like working at Apollo, you can find more information here.

ABOUT THE TEAM

The current evals team consists of Jérémy Scheurer, Alex Meinke, Bronson Schoen, Felix Hofstätter, Axel Højmark, Teun van der Weij, Alex Lloyd and Mia Hopman. Alex Meinke coordinates the research agenda with guidance from Marius Hobbhahn, though team members lead individual projects. You will mostly work with the evals team as well as our team of software engineers, but you will likely sometimes interact with the governance team to translate technical knowledge into concrete recommendations. You can find our full team here.

Equality Statement: Apollo Research is an Equal Opportunity Employer. We value diversity and are committed to providing equal opportunities to all, regardless of age, disability, gender reassignment, marriage and civil partnership, pregnancy and maternity, race, religion or belief, sex, or sexual orientation.

How to apply: Please complete the application form with your CV. The provision of a cover letter is optional but not necessary. Please also feel free to share links to relevant work samples.

About the interview process: Our multi‑stage process includes a screening interview, a take‑home test (approx. 2.5 hours), 3 technical interviews, and a final interview with Marius (CEO). The technical interviews will be closely related to tasks the candidate would do on the job. There are no LeetCode‑style general coding interviews. If you want to prepare for the interviews, we suggest working on hands‑on LLM evals projects (e.g. as suggested in our starter guide); such as building LM agent evaluations in Inspect.