Research Engineer, Frontier Safety Mitigations, DeepMind
Research Engineer, Frontier Safety Mitigations, DeepMind Overview
| Company Name | |
| Job Role | Research Engineer, Frontier Safety Mitigations, DeepMind |
| Qualifications | Bachelor’s |
| Category | IT Jobs |
| Job Type | Full Time |
| Location | London |
In this position, you will focus on mitigating risks associated with model launches by defending against various misuse domains, including cybersecurity and harmful manipulation. Your responsibilities will include building evaluations, conducting red-teaming exercises, researching and deploying mitigations, and monitoring emerging risks to ensure the beneficial use of technology.
The Frontier Safety Mitigation team operates within the Gemini Safety team and is committed to developing safety mitigations for advanced models. This role emphasizes the importance of proactively researching and implementing defense-in-depth strategies as AI technology evolves.
Responsibilities
- Develop advanced classifiers and data pipelines to identify misuse, managing the entire process from automated evaluation to rapid model iteration.
- Create cross-context monitoring systems to detect coordinated harms, employing innovative signal aggregation techniques across various user sessions to pinpoint large-scale attack vectors.
- Implement data-driven, semi-automated account-level response systems to identify, track, and counteract persistent malicious actors using comprehensive signals from production traffic.
- Evaluate and secure agentic AI systems by formulating threat models, establishing testing environments, and deploying effective mitigations against frontier-level agentic hacking and long-term attacks.
- Advance research in automated red-teaming and adversarial robustness, utilizing multi-turn/agentic attacks to systematically identify and expose misuse vulnerabilities.
Requirements
- A Bachelor’s degree or equivalent practical experience is required.
- At least 5 years of experience in software development using one or more programming languages.
- Minimum of 3 years of experience in testing, maintaining, or launching software products, along with 1 year of experience in software design and architecture.
- A PhD in Computer Science, Machine Learning, or a related field is preferred, or a record of publications in notable venues such as NeurIPS, ICLR, ICML, or EMNLP.
- Experience in cybersecurity detection and response, including the development of classifiers and anomaly detection systems at scale.
- Familiarity with taking safety defenses or mitigations from research concepts to scalable production systems.
- Knowledge in adversarial machine learning, automated red-teaming, or model interpretability and probes.
- Experience in collaborating on or leading applied machine learning projects, including training, inference, and fine-tuning of large language models.
- Proficiency in using AI coding agents with strong architectural judgment, as well as experience with TPUs and JAX.
- Understanding of AI control, chain-of-thought monitoring, monitorability, and related frontier safety research.
Benefits
- Opportunity to work in a collaborative environment with a strong culture of support and teamwork.
- Engagement in a dedicated scientific community focused on solving intelligence and ensuring technology benefits the public.
- Access to diverse learning opportunities and varied career pathways within a pioneering AI lab.
Degree Requirement: Bachelor’s
Visa Sponsorship May be
To apply for this job please visit www.google.com.