Research Engineer, Responsible AI & Safety Frameworks

DeepMind Technologies Limited; Greater London; On-site; GBP 90,000 - 140,000; Full time

Job summary

DeepMind Technologies Limited is seeking a highly adaptable Research Engineer to join the Responsibility team. You will design and scale evaluation frameworks that assess the propensity of frontier language models to engage in harmful manipulation, develop evaluation and mitigation techniques for manipulative model behaviors, and build infrastructure to track model performance across releases.

You will work closely with Research Scientists, safety policy teams, and product stakeholders to ensure

Qualifications

• Bachelor's degree in Computer Science, Machine Learning, Mathematics, or a related technical field, or equivalent practical experience.
• 3 years of experience in Python programming.
• 3 years of experience with ML frameworks such as JAX, PyTorch, or TensorFlow.

Responsibilities

• Rapidly prototype and deliver scalable engineering solutions across the Responsibility research portfolio.
• Architect and optimize training and inference pipelines to detect and evaluate harmful manipulation behaviors in frontier language models.
• Develop post-training strategies to mitigate manipulation risks including deceptive persuasion, sycophancy, and covert influence tactics.
• Collaborate with research scientists to translate safety research into robust implementations and present results to cross-functional stakeholders.
• Build and maintain evaluation infrastructure to systematically track model safety performance across releases.

Skills

Python

JAX

PyTorch

TensorFlow

Education

BSc in CS/ML/Math or related field

MS or PhD in CS/Engineering/ML

Tools

C++

Job description

DeepMind Technologies Limited is seeking a highly adaptable Research Engineer to join the Responsibility team. You will design and scale evaluation frameworks that assess the propensity of frontier language models to engage in harmful manipulation, develop evaluation and mitigation techniques for manipulative model behaviors, and build infrastructure to track model performance across releases.

You will work closely with Research Scientists, safety policy teams, and product stakeholders to ensure