В Google DeepMind это чётко очерченная senior-роль на переднем крае безопасности ИИ, с работой от исследований до продакшена и сильной карьерной ценностью; условия оплаты не указаны.
Передовой ИИ
Понятные задачи
Современный стек
Сильная лаборатория
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Frontier Safety Mitigations Research Engineer (AI): Building classifiers, monitoring systems, data pipelines, and mitigations to detect misuse and secure frontier AI and agentic systems with an accent on adversarial robustness, automated evaluation, and large-scale threat detection. Focus on designing cross-context signal aggregation, developing account-level response systems, and testing long-horizon agentic attacks.
Location: London, UK
Company
Google DeepMind is an AI research lab advancing artificial intelligence for scientific discovery, product innovation, and public benefit, with safety and ethics as core priorities.
What you will do
Build advanced classifiers and data pipelines to detect misuse, owning the process from automated evaluation through rapid model iteration.
Develop cross-context monitoring systems and signal aggregation methods to detect coordinated harms and large-scale attack vectors.
Implement semi-automated account-level response systems that detect, track, and apply strikes against persistent malicious actors using production-traffic signals.
Evaluate and secure agentic AI systems by creating threat models, testing environments, and mitigations for agentic hacking and long-horizon attacks.
Advance automated red-teaming and adversarial robustness research through multi-turn and agentic attacks that uncover misuse vulnerabilities.
Requirements
Bachelor's degree in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience.
At least 5 years of software development experience, including Python.
Experience with the research-to-deployment pipeline in a frontier AI environment.
Experience working in a software engineering or research team.
Nice to have
Experience with cybersecurity detection and response, classifiers, anomaly detection systems at scale, and taking safety mitigations from research concepts to scalable production systems.
Experience collaborating on or leading applied ML projects, including LLM training, inference, and fine-tuning.
Experience with AI coding agents, strong architectural judgment, 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.
Culture & Benefits
Work with interdisciplinary, global teams focused on advancing AI and addressing complex global challenges.
Collaborate in an environment emphasizing collective effort, scientific discovery, safety, and ethics.
Location-based role in London, UK.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →