Research Engineer, Responsibility Engineering, DeepMind

Requirements:

• Bachelor's degree in Computer Science, Machine Learning, Mathematics, or a related technical field, or equivalent practical experience.
• 8 years of experience in machine learning engineering or large-scale software systems.
• 3 years of experience in Python programming.
• 3 years of experience with ML frameworks such as JAX, PyTorch, or TensorFlow.

Nice to Haves:

• Master's degree or PhD in Computer Science, Engineering, or a related field with a focus on Machine Learning.
• Experience working directly on AI safety, adversarial robustness, jailbreak evaluation, or responsible AI research.
• Experience in Python and C++ for high-performance ML library development.
• Experience with adversarial machine learning, red-teaming, AI safety evaluation, or security research.
• Experience building evaluation frameworks, benchmarks, or automated testing pipelines for ML models.

What You'll Be Doing:

• Prototype and deliver scalable engineering solutions rapidly.
• Architect and optimize training and inference pipelines to evaluate the frontier language models.
• Develop post-training strategies to mitigate adversarial risks including jailbreak and prompt injection attacks.
• Collaborate with Research Scientists to translate safety research into implementations and present results to cross-functional stakeholders.
• Build and maintain evaluation infrastructure to systematically track model safety performance.

Perks and Benefits:

• Opportunity to work at Google DeepMind, a pioneering AI lab.
• Engage in cutting-edge AI research and development.
• Exceptional interdisciplinary teams focused on solving complex global challenges.
• Diverse learning opportunities and varied career pathways.