Evals Platform Engineer, Apollo Research
We can sponsor UK visas
5+ days a week in office
AI evals research organisation
Be an early applicant
AI evals research organisation
1-20 employees
Be an early applicant
We can sponsor UK visas
5+ days a week in office
1-20 employees
Company mission
To reduce dangerous capabilities in advanced AI systems, especially deceptive behaviors.
Role
Who you are
- Experience leading infrastructure projects from start to finish
- Experience implementing security best practices for cloud and containerised environments
- Solid knowledge of AWS, including IAM and EKS
- Strong hands-on experience with Kubernetes
- Bonus: experience with cillium, gVisor, Karpenter
- Experience with Infrastructure as Code toolsStrong software engineering skills, preferably in Python
- Bonus: Experience setting up and maintaining data collection, monitoring, and alerting systems
What the job involves
- We're seeking a Platform Engineer who will design, build, and maintain the secure infrastructure foundation that powers our frontier AI evaluations
- As the infrastructure specialist on our team, you'll have broad decision-making authority over our tech stack and directly enable our research mission through robust, scalable systems
- What You'll Accomplish in Your First Year
- Accelerate our frontier LLM evaluations research by building an internal platform with both robust backend infrastructure and intuitive researcher-facing interfaces
- Define the vision and roadmap for the team’s infrastructure that securely and reliably supports our research
- Establish a comprehensive security posture across our cloud resources and deployments to protect sensitive data and maintain the trust of our partners
- Optimize infrastructure costs, ensuring efficient use of resources as our demand increases
- Design, implement, scale, and maintain infrastructure for running frontier LLM evals using Infrastructure as Code (IaC)
- Choose and integrate appropriate technologies for our infrastructure stack (e.g. decision to adopt Kubernetes)
- Collaborate with software engineers to build internal software tools that leverage our infrastructure, for tasks including job orchestration, project access, results storage, and more
- Administer and secure internal AWS accounts (IAM, resource deployments, spending, etc)
- Help set up and manage organisation-wide security processes
- Additionally, you are someone who will:
- Take ownership of our infrastructure and drive solutions from concept to implementation
- Balance security requirements with researcher productivity
- Communicate complex technical concepts clearly to both technical and non-technical team members
- Anticipate infrastructure needs before they become bottlenecks
- Respond to user requests with fast turnaround
- Advocate for good security practices in the team
Application process
- The final date for submissions is 25 April 2025
- Our multi-stage process includes a screening interview, a take-home test (approx. 2 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
- Start Date: Target of 2-3 months after the first interview
Salary benchmarks
Our take
Apollo Research is an organisation dedicated to understanding and reducing the risks associated with advanced AI systems, particularly those that exhibit deceptive behaviours. It does so by focusing on evaluating AI models for strategic deception, conducting interpretability research to make AI more understandable, and providing technical guidance to global policymakers on how to handle these emerging technologies.
AI is rapidly advancing so the work Apollo is doing has come at a crucial time. As AI systems grow more powerful, the risks associated with them also become more pressing and Apollo's approach, which combines in-depth model evaluation with cutting-edge interpretability research, helps reduce these risks. Its an exciting initiative that not only ensures AI is safe but could also help shape the future of responsible AI development.
Steph
Company Specialist at Welcome to the Jungle
Company
Company benefits
- 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 $1000 (USD) professional development budget
Company HQ
London, UK
Leadership
Marius Hobbhahn
(Co-Founder & Director)Graduated from the University of Tübingen with an MS in Machine Learning.
Christopher Akin
(COO)Previously a Strategy Consultant at CLA Consulting, a VP of Global Sales at BURN Manufacturing, Founder of The Base Project and Locean Labs, and COO of ADWALLS.
Share this job