Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Staff+ Software Engineer (AI Safeguards): Building monitoring, abuse detection, and multi-layered intervention systems that protect AI products and detect unwanted model behavior with an accent on trust and safety, agent security, and large-scale data infrastructure. Focus on designing real-time enforcement systems, distributed investigation tooling, and adversarial-input defenses across Anthropic's products and APIs.
Location: San Francisco, CA or New York City, NY; hybrid work with at least 25% office attendance
Annual salary: $320,000–$485,000 USD
Company
Anthropic is a public benefit corporation building reliable, interpretable, and steerable AI systems designed to be safe and beneficial for users and society.
What you will do
- Develop monitoring systems that detect unwanted behavior from API partners and support automated enforcement and analyst review.
- Build abuse detection mechanisms and infrastructure for Anthropic products, APIs, and third-party clouds.
- Surface abuse patterns to research teams to strengthen models during training.
- Build reliable, multi-layered safety defenses that improve in real time and operate at scale.
- Develop safeguards acceleration systems, intervention tooling, and data intelligence infrastructure across multiple teams.
Requirements
- Bachelor’s degree in Computer Science, Software Engineering, or comparable experience.
- Proficiency in Python and TypeScript.
- Ability to work across the stack and explain complex technical concepts to non-technical stakeholders.
- Experience requirements will correlate with the internal job level; strong candidates may have 8+ years of software engineering experience.
- Ability to work from the San Francisco or New York City office at least 25% of the time.
Nice to have
- Experience with integrity, spam, fraud, or abuse detection and mitigation.
- Experience building trust and safety detection or intervention mechanisms for AI/ML systems.
- Experience with prompt engineering, jailbreak attacks, and adversarial inputs.
- Experience working with operational teams to build custom internal tooling.
Culture & Benefits
- Collaborative work across large-scale AI research and engineering efforts.
- Flexible working hours and an office environment for collaboration.
- Generous vacation and parental leave.
- Competitive compensation and benefits, including optional equity donation matching.
- Visa sponsorship is available, with immigration lawyer support, subject to role and candidate eligibility.
Hiring process
- Team placement takes place after the interview process based on interests, experience, and organizational needs.
- Applications are reviewed on a rolling basis with no stated deadline.
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 →
Похожие вакансии
9 дней назад
Staff Software Engineer (AI Systems)
215 000 - 250 000$
6 дней назад
Forward Deployed Engineer (AI Supply Chain)
197 000 - 285 000$
5 дней назад
Staff Software Engineer (AI/Trust & Safety)
255 000 - 285 000$
5 дней назад
Staff Software Engineer, Agentic AI
151 000 - 297 000$
6 дней назад
Software Engineer (AI)
210 000 - 265 000$
6 дней назад
Head of Software Engineering (AI)
237 000 - 340 000$