Senior AI Security Researchers

What you'll do

• Design and execute realistic AI attack simulations to inform security product development.
• Perform hands-on attacks including prompt injections, jailbreaks, and multimodal injections.
• Build scalable AI red teaming tooling and automation for large-scale evaluations.
• Translate research findings into practical mitigations like input filters and agent guardrails.
• Evaluate the effectiveness of existing AI defenses and provide strategic recommendations.
• Research emerging attacker techniques and map them to industry frameworks like MITRE ATLAS.
• Deliver technical reports and actionable briefings to executive leadership.
• Mentor team members and shape long-term AI simulation methodologies.

What we're looking for

• Must have a Doctorate in a relevant field with 3+ years of experience, a Master's with 3+ years, or a Bachelor's with 4+ years of experience.
• Must have equivalent experience to the degree and years of experience requirements.
• Must be able to pass the Microsoft background and Microsoft Cloud background check.
• Must have 6+ years of experience in security research and/or AI/ML security (preferred).
• Must have a security background in finding and exploiting real vulnerabilities with an adversarial mindset (preferred).
• Must have a practical understanding of modern AI, including LLMs, RAG, fine-tuning, and agentic systems (preferred).
• Must have hands-on experience attacking AI systems, including prompt injection, jailbreaks, and guardrail bypass (preferred).
• Must have Python skills for building attack automation and research tooling (preferred).