Research Engineer, Responsible Frontier AI Research, DeepMind

Overview

In this role, you will prototype and deliver scalable ML solutions for safety-focused research across a multi-disciplinary portfolio. You will architect training and inference pipelines to detect harmful manipulation in frontier language models and develop post-training strategies to mitigate deceptive tactics. You’ll collaborate with researchers to translate safety findings into robust implementations and build evaluation infrastructure to track safety performance across releases. You will contribute to a mission-driven team that prioritizes safety, ethics, and real-world impact at scale.

Responsibilities

• Prototype and deliver scalable engineering solutions across the safety research portfolio
• Architect and optimize training and inference pipelines for detection of harmful manipulation in language models
• Develop post-training mitigation strategies for manipulation risks such as deceptive persuasion and covert influence
• Collaborate with researchers to translate safety research into robust implementations and present results to cross-functional stakeholders
• Build and maintain evaluation infrastructure to track model safety performance across releases

Key requirements

• Bachelor in Computer Science, Machine Learning, Mathematics, or related 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

• collaboration with researchers
• cross-functional communication
• problem solving under safety constraints
• Python programming
• ML frameworks: JAX, PyTorch, TensorFlow
• high-performance ML library development (C++ experience)

…