> Markdown version of [/jobs/ext/3614046-frontier-safety-mitigations-research-engineer-deepmind](https://www.wearedevelopers.com/jobs/ext/3614046-frontier-safety-mitigations-research-engineer-deepmind). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Frontier Safety Mitigations Research Engineer, DeepMind

- **Company:** Google
- **Location:** London, UK
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Monitoring of Systems, Python (Programming Language), Machine Learning, Performance Tuning, Software Engineering, Delivery Pipeline, Large Language Models, AI Coding Agents, Information Technology, Data Analytics, DeepMind, Data Pipelines
- **Published:** October 8, 2026
- **Apply:** https://dejobs.org/x/x/566E82674B2D4555BED4A0947AB10849/job/

## About the Role

* Bachelor's degree in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience.
 * 5 years of experience in software development, including experience with Python.
 * Experience with the research-to-deployment pipeline in a frontier AI environment.
 * Experience working in a software engineering or research team., * Experience with cybersecurity detection and response, building classifiers and anomaly detection systems at scale, taking safety defenses or mitigations from research concepts to scalable production systems.
 * Experience collaborating on or leading applied ML projects, including LLM training, inference, and fine-tuning.
 * Experience using AI coding agents with strong architectural judgement, and with TPUs and JAX.
 * Background in adversarial machine learning, automated red-teaming, or model interpretability and probes.
 * Knowledge of AI control, chain-of-thought monitoring, faithfulness, monitorability, and related frontier safety research.

## Description

* 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, developing novel signal aggregation methods across disparate user sessions to identify large-scale attack vectors.
 * 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.
 * 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.
 * Advance research in automated red-teaming and adversarial robustness, leveraging multi-turn/agentic attacks to systematically test for and uncover misuse vulnerabilities.