Senior AI/LLM Threat Researcher (Cybersecurity)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Senior AI/LLM Threat Researcher (Cybersecurity): Identifying, documenting, and mitigating emerging threats against Large Language Models and AI Agents with an accent on security boundaries in Agentic Loops and multi-step reasoning. Focus on developing methodologies to test the robustness of RAG pipelines and ensuring resilience against adversarial inputs.
Location: Must be based in or able to commute to Sunnyvale, CA (Hybrid: 2-3 days per week on-site)
Salary: $140,000 - $215,000 per year
Company
A global leader in cybersecurity providing an AI-native platform to stop breaches and protect modern organizations.
What you will do
- Conduct deep-dive analysis into LLM architectures and agentic frameworks to identify security weaknesses.
- Evaluate security boundaries in Agent-to-LLM and Agent-to-Application interactions.
- Develop methodologies to test the robustness of RAG pipelines and third-party tool integrations.
- Map research findings and defensive strategies to industry standards like MITRE ATLAS and OWASP.
- Contribute to the security community by publishing whitepapers and presenting research at industry conferences.
Requirements
- Must be based in the USA
- Comprehensive understanding of transformer architectures, attention mechanisms, and LLM development lifecycles.
- Expertise in AI orchestration frameworks and security implications of autonomous decision-making.
- Proficiency in Python and experience with AI security evaluation or red-teaming methodologies.
- Knowledge of the evolving LLM risk landscape, including prompt injection and data integrity.
- Familiarity with emerging AI protocols such as MCP and A2A.
Nice to have
- Record of academic publications or public research regarding AI/ML security.
- Experience in AI red teaming or security evaluation programs.
- Experience developing defensive layers like guardrail systems or monitoring solutions.
Culture & Benefits
- Market-leading compensation and equity awards.
- Comprehensive physical and mental wellness programs.
- Competitive vacation and holiday policies.
- Paid parental and adoption leaves.
- Professional development opportunities and vibrant office culture.
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 →