Job description
SaferAI • Paris / London / San Francisco Bay Area
SaferAI is a fast-moving, mission-driven organization advancing and promoting AI risk management to reduce AI risks, in particular extreme risks from advanced AI systems. We’re uniquely positioned at the intersection of technical research work and policy, ensuring that the knowledge we produce has an impact on AI risk management.
SaferAI’s work centers around frontier AI risk management, and we have been responsible for major contributions to AI risk management of general-purpose AI models. We are a primary contributor to EU risk management standards, and we were influential in drafting the EU GPAI Code of Practice. We released the first AI risk management framework that combines traditional risk management and frontier AI safety policies, co-drafted G42’s Frontier AI Safety policy and advised several other frontier AI companies on their policies and practices. We developed the first AI risk management assessment of AI companies’ risk management practices, informing the decisions of major investors. We developed a methodology for quantitative risk modeling, applied it to develop nine cybersecurity risk models, and are now implementing risk modeling as part of the EU Commission tender and partnering with multiple AI safety institutes globally.
ResponsibilitiesThis role will join the Evaluations team and help improve how leading AI labs track and manage risk. The evaluations team runs model evaluations and delivers risk reports to leading AI labs and supports them with improving their safety practices. For our model evaluations, we use METR’s Hawk platform to run Inspect AI on AWS.
As a Founding Engineer, you will have two responsibilities. First, improve and maintain our cloud infrastructure for running model evaluations while maintaining excellent cybersecurity practices to safeguard sensitive lab data. Note that frontier labs trust us with sensitive model access and data, so data security is mission-critical for us. Second, directly drive the team’s model evaluation and mitigations work. This can be led by your skills and experience but could include upstreaming modifications to Inspect AI to facilitate our evaluation needs, identifying the most relevant available benchmarks to measure risk, running those benchmarks on AI models while ensuring strong elicitation and quality control, and analyzing the results. It could also include developing demonstrations of safety mitigations, developing products and tools to mitigate risk, and supporting leading AI labs with mitigation implementation.
The exact focus of the research engineering part of the role will be informed by your interest and experience level. This could be an excellent opportunity for someone with strong platform skills and an interest in AI Safety to move into a technical AI Safety role.
SaferAI has begun performing safety evaluations for frontier developers and is in active discussions with others across European, US and East Asian markets. This is a rare opportunity to shape how the world’s most capable AI companies manage risk.
This role will join a new team on a rapid growth trajectory. This is a chance to learn fast and take on significant responsibility early. Your decisions and ability to deliver will make an immediate difference to the team’s impact.
Note that we are also hiring a Research Scientist/Engineer.
What we’re looking forTechnical expertise
- Strong experience with AWS (or another cloud provider) with depth in EKS/Kubernetes, including Helm and Karpenter
- Experience using Infrastructure as Code with either Pulumi, Terraform, or similar
- Python (production-ready preferred)
- CI/CD workflows (GitHub Actions preferred)
- PostgreSQL operations including RLS
- Security engineering fundamentals: zero-trust network access (Tailscale ACLs, subnet routers), Kubernetes network policy for pod isolation, AWS GuardDuty for monitoring, least-privilege IAM, secrets management
- Nice to have: Cilium network policies, Cognito, Tailscale, Datadog
Note: we’re also open to considering exceptional software engineers with limited platform experience who are keen to build these skills quickly.
Background and professional experience
- 3+ years of professional experience in platform, infrastructure, or DevOps roles, ideally in a small team where you owned systems end-to-end
- Experience supporting teams to deliver projects in fast-paced and constantly evolving environments.
Practical problem-solving
- Comfortable with ambiguity and able to provide “good enough” solutions to open-ended problems and switch between problems to prioritize the most impactful opportunities.
- Exceptional problem-solving skills and skills in thinking logically about the big picture, identifying areas of improvement, and driving change.
Delivery and project management
- Ability to produce clear written deliverables such as gap analyses, methodology documents, or implementation roadmaps under time pressure and with incomplete information.
- Comfort operating in a fast-moving, under-defined field where precedent is scarce and judgment must substitute for established playbooks.
- Highly collaborative and service-oriented, used to working in diverse teams.
- Ability to work effectively in a remote, asynchronous, and international environment
Mission alignment
- Alignment with SaferAI’s mission to ensure that advanced AI technologies are safe through risk management practices, policy, and safe technology development.
Bonus: technical AI literacy
The following are not essential for the role but are nice to have:
- Hands-on technical experience with AI systems development, deployment, or safety engineering at a frontier AI company, AI product company, or AI research organization.
- Familiarity with AI safety and evaluation methodologies, including capability evaluations, red-teaming, safety cases, and model cards, and the ability to assess their efficacy.
- Hands-on experience running model evaluations, including with LLM provider APIs and Inspect AI
- Familiarity with AGI safety and governance work, alongside safety and policy issues related to technology and society more broadly.
Bonus: Chinese language
Chinese language skills would be a significant plus, as we sometimes speak with technical staff at Chinese frontier AI labs.
What we offerWork location: SaferAI’s team members are mostly based in Paris and London, and we are setting up a presence in the San Francisco Bay Area. We have a preference for new joiners to be based at one of these locations. However, we are willing to consider remote arrangements for particularly strong candidates. We work in English and French language skills are not required for this position.
Compensation: We offer a competitive salary for the European technical AI Safety ecosystem, commensurate with experience and location.
Benefits:
- Health insurance coverage and retirement plans adapted to the location
- Transportation home to work covered at 50%
- Productivity expenditures up to €2k annually
- Office space if relevant
To apply for this position, please complete this application form. We will evaluate candidates on a rolling basis starting now until we fill the role. We are aiming to fill the role quickly, and we’ll take down the page on our website as soon as the role is filled.
Our hiring process comes in stages and usually consists of initial screening, a first interview, a paid work test, interviews, and a final 3-day paid work trial where you would directly collaborate with the team.
We encourage you to lean towards applying, even if you don’t have all the skills and experience required.
If you have any questions or concerns throughout the application process, please don’t hesitate to reach out to us at careers@safer-ai.org. We look forward to reviewing your application.