Frontier Safety Mitigations Engineer (Applied ML & Adversarial)

Google; United Kingdom; On-site; GBP 120,000 - 180,000; Full time

Job summary

Google DeepMind is seeking a skilled AI software engineer to develop advanced classifiers and data pipelines aimed at detecting misuse, leading end-to-end evaluation and rapid model iteration. The role requires at least five years in software development, including Python, and experience with the research-to-deployment pipeline in frontier AI.

You will contribute to cross-context monitoring, threat modeling, and robust mitigations while collaborating with interdisciplinary teams focused on safe

Qualifications

• Bachelor's degree in Computer Science, Machine Learning, or related field or equivalent practical experience.
• 5 years of experience in software development, including Python.
• Experience with the research-to-deployment pipeline in a frontier AI environment.
• Experience working in a software engineering or research team.

Responsibilities

• Build advanced classifiers and data pipelines to detect misuse, and own the end-to-end process from automated evaluation to rapid model iteration.
• Build cross-context monitoring systems to detect coordinated harms and identify large-scale attack vectors.
• Implement data-driven, semi-automated account-level response systems to detect and act against persistent malicious actors.
• Evaluate and secure agentic AI systems by developing threat models, testing environments, and deploying robust mitigations.
• Advance research in automated red-teaming and adversarial robustness through multi-turn/agentic attacks.

Skills

Python

Software development

Research deployment

Team collaboration

Education

Bachelor's degree in CS/ML

Tools

TPUs

JAX

Job description

Google DeepMind is seeking a skilled AI software engineer to develop advanced classifiers and data pipelines aimed at detecting misuse, leading end-to-end evaluation and rapid model iteration. The role requires at least five years in software development, including Python, and experience with the research-to-deployment pipeline in frontier AI.

You will contribute to cross-context monitoring, threat modeling, and robust mitigations while collaborating with interdisciplinary teams focused on safe