Research Engineer, Frontier Safety Mitigations, Deepmind

Google Google · Big Tech · San Francisco, CA +2

Research Engineer focused on developing and deploying advanced safety mitigations for frontier AI models, specifically defending against misuse in domains like Cybersecurity and CBRNE. The role involves building classifiers, data pipelines, monitoring systems, and evaluating agentic AI systems, with a strong emphasis on automated red-teaming and adversarial robustness.

What you'd actually do

  1. Build advanced classifiers and data pipelines to detect misuse, owning the end-to-end process from automated evaluation to rapid model iteration.
  2. Build cross-context monitoring systems to detect coordinated harms, developing novel signal aggregation methods across disparate user sessions to identify large-scale attack vectors.
  3. Implement data-driven, semi-automated account-level response systems to detect, track, and apply strikes against persistent malicious actors using rich signals from production traffic.
  4. Evaluate and secure agentic AI systems by developing threat models, creating testing environments, and deploying robust mitigations against frontier-level agentic hacking and long-horizon attacks.
  5. Be able to advance research in automated red-teaming and adversarial robustness, leveraging multi-turn/agentic attacks to systematically test for and uncover misuse vulnerabilities.

Skills

Required

  • software development
  • software design and architecture
  • research-to-deployment pipeline in a frontier AI environment

Nice to have

  • PhD in Computer Science or Machine Learning
  • publications at venues such as NeurIPS, ICLR, ICML, or EMNLP
  • cybersecurity detection and response
  • building classifiers and anomaly detection systems at scale
  • taking safety defenses or mitigations from research concepts to scalable production systems
  • collaborating on or leading applied ML projects
  • LLM training, inference, and fine-tuning
  • AI coding agents
  • TPUs and JAX
  • AI control
  • chain-of-thought monitoring
  • faithfulness
  • monitorability
  • frontier safety research
  • adversarial machine learning
  • automated red-teaming
  • model interpretability and probes

What the JD emphasized

  • critical misuse domains
  • advanced mitigations
  • highly robust
  • frontier models
  • highly applied
  • robust, end-to-end defenses
  • severe risks
  • Frontier Safety Framework commitments
  • frontier AI environment
  • scalable production systems
  • frontier safety research
  • adversarial machine learning
  • automated red-teaming
  • model interpretability

Other signals

  • building novel evaluations
  • researching and deploying advanced mitigations
  • secure agentic AI systems
  • threat models
  • testing environments
  • robust mitigations
  • automated red-teaming
  • adversarial robustness
  • multi-turn/agentic attacks
  • misuse vulnerabilities