Это высокоуровневая позиция на переднем крае исследований безопасности ИИ в ведущей мировой лаборатории, предлагающая серьезные технические вызовы и значительный профессиональный рост.
Трендовый домен
Масштабные задачи
Современный стек
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Research Engineer (AI Safety) (LLM Safety and Frontier Risk Mitigations): Building end-to-end defenses for frontier AI models, including misuse classifiers, monitoring systems, account-level response systems, and agentic AI security evaluations with an accent on automated evaluation, production-scale data pipelines, and adversarial robustness. Focus on detecting coordinated harms, modeling long-horizon agentic attacks, and advancing automated red-teaming against severe misuse risks.
Location: Mountain View, CA, USA
Salary: $174,000–$252,000 USD annually, plus a 15% bonus target, equity, and benefits.
Company
An AI research laboratory developing advanced artificial intelligence for scientific discovery, product innovation, and widespread public benefit, with safety and ethics as priorities.
What you will do
Build advanced classifiers and data pipelines to detect misuse, covering automated evaluation through rapid model iteration.
Develop cross-context monitoring systems and signal aggregation methods to identify coordinated harms and large-scale attack vectors across user sessions.
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 developing threat models, testing environments, and mitigations for frontier-level agentic hacking and long-horizon attacks.
Advance automated red-teaming and adversarial robustness research using multi-turn and agentic attacks to uncover misuse vulnerabilities.
Requirements
Bachelor’s degree or equivalent practical experience.
At least 5 years of software development experience in one or more programming languages.
At least 3 years of experience testing, maintaining, or launching software products, including 1 year of experience with software design and architecture.
Nice to have
Master’s degree or PhD in Computer Science or a related technical field.
Experience with large language model development, fine-tuning, or safety evaluation methodologies.
Experience taking research from concept to product.
Experience in safety and alignment.
Culture & Benefits
Work in a fast-paced, highly collaborative research environment focused on robust frontier-model safety mitigations.
Join an interdisciplinary scientific community working on complex global challenges and public-benefit applications of AI.
Receive a 15% bonus target, equity, and company benefits in addition to base salary.
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 →