Senior AI Safety Researcher — Lead Alignment & Robustness

AI Breaking Wire; Greater London; Hybrid; GBP 110,000 - 170,000; Full time

Benefits offered by this job

Stock options

Health programs and wellness benefits

Learning and development allowances

Volunteer days & matching charitable

Job summary

Google DeepMind is seeking a Senior AI Safety Researcher to lead research on alignment, interpretability, robustness, and mitigation of societal risks in advanced ML systems. You will develop evaluation frameworks and collaborate with product teams to embed safety guardrails in deployed models.

The role involves publishing in top venues, advancing safety methodologies, and guiding interdisciplinary research efforts within a leading AI lab.

Qualifications

• Ph.D. or equivalent practical experience in Machine Learning, Computer Science, Cognitive Science, or Philosophy.
• Extensive publication record in AI safety, alignment, interpretability, or robust machine learning.
• Strong proficiency in Python and modern deep learning libraries.

Responsibilities

• Conduct fundamental and applied research on AI safety, alignment, and model robustness.
• Develop novel evaluation frameworks to detect vulnerabilities, hallucinations, and harmful outputs.
• Partner with product and engineering teams to integrate safety guardrails into deployed systems.
• Author research papers for top-tier academic venues (NeurIPS, ICML, ICLR).

Skills

Python

Deep learning libraries

Education

Ph.D. or equivalent practical experience in ML/CS/ Cognitive Science/Philosophy

Job description

Google DeepMind is seeking a Senior AI Safety Researcher to lead research on alignment, interpretability, robustness, and mitigation of societal risks in advanced ML systems. You will develop evaluation frameworks and collaborate with product teams to embed safety guardrails in deployed models.

The role involves publishing in top venues, advancing safety methodologies, and guiding interdisciplinary research efforts within a leading AI lab.