Research Engineer
Autonomous Systems
We're focused on loss of control risks from frontier AI systems. To address this, we're advancing the state of the science in risk modeling, incorporating insights from other safety-critical and adversarial domains, while developing our own novel techniques. Additionally, we're empirically evaluating these risks - building out one of the world's largest agentic evaluation suites, as well as pushing forward the science of model evaluations, to better understand the risks and predict their materialisation. Lastly, we are developing novel mitigations that, for example, attempt to prevent models from intentionally underperforming on dangerous capability evaluations.
Role Summary
As a research engineer, you'll work as part of a multi-disciplinary team including scientists, engineers and domain experts on the risks that we are investigating. Your team is given huge amounts of autonomy to chase research directions & build evaluations that relate to your team’s over-arching threat model. This includes coming up with ways of breaking down the space of risks, as well as designing & building ways to evaluate them. All of this is done within an extremely collaborative environment, where everyone does a bit of everything. Some of the areas we focus on include:
- Self-replication: Researching the potential for AI systems to autonomously replicate themselves across networks and establish persistence.
- AI R&D: Investigating AI systems' potential to iteratively improve themselves, potentially leading to an intelligence explosion.
- Safety sabotage: Evaluating AI systems' potential to sabotage safety - for example by sabotaging safety research.
You’ll receive coaching from your manager and mentorship from the principal research engineer on our team. We have a very strong learning & development culture to support this, including Friday afternoons devoted to deep reading and various weekly paper reading groups.
Person Specification
You may be a good fit if you have some of the following skills, experience and attitudes. Please note that you don’t need to meet all of these criteria, and if you're unsure, we encourage you to apply.
- Writing production quality code.
- Designing, shipping, and maintaining complex tech products.
- Improving technical standards across a team, through mentoring and feedback.
- Strong written and verbal communication skills.
- Experience working within a multi-disciplinary team comprised of both scientists and engineers.
- Strong understanding of large language models. This can include a broad understanding of the literature, and/or hands-on experience with things like pre-training or fine tuning LLMs.
- Extensive Python experience, including the wider ecosystem and tooling.
Salary & Benefits
We are hiring individuals at all ranges of seniority and experience within this research unit, and this advert allows you to apply for any of the roles within this range. Your dedicated talent partner will work with you as you move through our assessment process to explain our internal benchmarking process. The full range of salaries are available below, salaries comprise of a base salary, technical allowance plus additional benefits as detailed on this page.
- Level 3 - Total Package £65,000 - £75,000
- Level 4 - Total Package £85,000 - £95,000
- Level 5 - Total Package £105,000 - £115,000
- Level 6 - Total Package £125,000 - £135,000
- Level 7 - Total Package £145,000
