TL;DR
Senior Security Engineer, Agentic Red Team (AI): Executing adversarial engagements, working with product builders to identify architectural flaws. Focus on performing complex, multi-turn attacks on production-level AI models and contributing to "Auto Red Teaming" frameworks.
Location: Mountain View, California, US; New York City, New York, US; Zurich, Switzerland.
Salary: $166,000 - $244,000 + bonus + equity + benefits
Company
hirify.global is a team of scientists, engineers, and machine learning experts advancing AI for public benefit and scientific discovery.
What you will do
- Conduct rapid security assessments on agentic services, focusing on GenAI vulnerabilities.
- Engineer complex attack sequences that exploit model behaviors and agentic logic errors.
- Write code to transform vulnerability discoveries into automated regression testing frameworks.
- Partner directly with developers to provide immediate feedback during the design phase.
- Maintain and expand a library of agent-specific attack patterns and exploit primitives.
Requirements
- Bachelor's degree in Computer Science, Information Security, or equivalent experience.
- Experience in Red Teaming, Offensive Security, or Adversarial Machine Learning.
- Strong coding skills in Python, Go, or C++ with experience building security tools or automation.
- Technical understanding of LLM architectures, agentic workflows, and common AI vulnerability classes.
Nice to have
- Hands-on experience developing exploits for GenAI models.
- Experience working in a consulting capacity with product teams or in a fast-paced environment.
- Familiarity with AI safety benchmarks, evaluation frameworks, and fuzzing techniques.
- Ability to translate complex probabilistic risks into actionable engineering fixes for developers.
Culture & Benefits
- Committed to equal employment opportunity regardless of sex, race, religion, ethnic origin, disability, age, citizenship, marital status, sexual orientation, gender identity, or pregnancy.
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 →