Research Engineer, Assurance Evaluation

The Rundown AI, Inc.; London; On-site; GBP 50,000 - 90,000; Full time

Job summary

An innovative company is seeking engineers passionate about AI to develop and execute evaluations for cutting-edge AI systems. In this role, you will maintain infrastructure for reliable evaluations and collaborate with experts in AI ethics, safety, and policy. Your work will directly inform release decisions and help ensure the safety of advanced AI models. If you have a strong technical background, especially in Python and machine learning, and a keen interest in AI ethics, this position offers a unique opportunity to contribute to the future of AI technology.

Qualifications

• Bachelor's degree in a relevant technical field or equivalent experience.
• Strong proficiency in Python and understanding of machine learning concepts.

Responsibilities

• Design and develop evaluations to test the safety of advanced AI models.
• Build and maintain evaluation infrastructure for AI systems.

Skills

Python

Machine Learning

Mathematics

Statistics

AI Ethics

Education

Bachelor's degree in a technical field

Tools

Data Analysis Tools

Job description

Snapshot

Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, we’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

About Us

Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, we’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

The Role

We’re looking for engineers interested in creating and executing evaluations to inform release decisions for our cutting-edge AI systems.

You will develop and maintain infrastructure and methods for reliable, repeatable evaluations, including datasets, systems for automated and human evaluations, and analysis tools.

You will stay informed about trends in AI development, governance, and sociotechnical research. Using this knowledge, you will help design new evaluations and clearly communicate results to advise decision-makers on AI safety.

In this role, you will collaborate closely with engineers and research scientists, including those focused on AI development, ethics, and policy.

Key responsibilities:

• Design and develop evaluations to test the safety of advanced AI models.
• Build and maintain evaluation infrastructure.
• Conduct evaluations prior to AI model releases.
• Communicate results effectively to decision-makers.
• Work with experts in AI ethics, policy, and safety.

About You

We look for the following skills and experience:

• Bachelor's degree in a technical field (e.g., machine learning, AI, computer science, mathematics, physics, statistics) or equivalent experience.
• Strong proficiency in Python.
• Understanding of mathematics, statistics, and machine learning concepts relevant to research papers.
• Ability to present technical results clearly.
• A keen interest in AI ethics, safety, and policy.

Preferred qualifications:

• Experience with crowd computing, designing experiments, or working with human raters.
• Experience in web application development and UX design.
• Familiarity with data analysis tools and libraries.
• Ability to manage projects with multiple stakeholders.

At Google DeepMind, we value diversity and are committed to equal employment opportunity. If you require accommodations due to disability or other needs, please let us know.

Application deadline: 5pm GMT, Wednesday 21st May 2025