Чётко очерченная инженерная роль в области безопасности ИИ в ведущей исследовательской лаборатории даёт редкий доступ к работе с передовыми моделями, хотя о команде и повседневных условиях сказано мало.
Передовой ИИ
Сильная исследовательская среда
Современный стек
?Высокий порог входа
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Research Engineer, Responsible Frontier AI Research, DeepMind (AI): Building scalable engineering solutions, training and inference pipelines, and evaluation infrastructure for detecting and mitigating harmful manipulation in frontier language models with an accent on AI safety, responsible AI, and high-performance ML systems. Focus on developing post-training strategies for deceptive persuasion, sycophancy, and covert influence, while translating safety research into robust implementations and tracking model performance across releases.
Location: London, UK
Company
Google DeepMind is an AI research lab focused on advancing artificial intelligence to address complex global challenges and support scientific discovery and product innovation, with safety and ethics as priorities.
What you will do
Prototype and deliver scalable engineering solutions across the Responsibility research portfolio.
Architect and optimize training and inference pipelines for detecting and evaluating harmful manipulation in frontier language models.
Develop post-training strategies to mitigate deceptive persuasion, sycophancy, and covert influence risks.
Build and maintain evaluation infrastructure to track model safety performance across releases.
Collaborate with Research Scientists to translate safety research into robust implementations and present results to cross-functional stakeholders.
Requirements
Master's degree or PhD in Computer Science or a related technical field.
Experience working on AI safety or responsible AI research.
Nice to have
Master's degree or PhD in Computer Science, Engineering, or a related field focused on Machine Learning.
Experience with Python and C++ for high-performance ML library development.
Experience with LLM demitigation, adversarial robustness, harmful manipulation detection, or AI safety evaluation and mitigation.
Experience building evaluation frameworks, benchmarks, or automated testing pipelines for ML models.
Prior experience working directly on AI safety or responsible AI research.
Culture & Benefits
Work in interdisciplinary teams advancing AI for public benefit and scientific discovery.
Collaborate with universities, technical institutes, and research programs worldwide.
Contribute to the wider research community through research partnerships and publishing papers.
Work on real-world AI engineering and research problems with opportunities for learning and career development.
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 →