Staff AI Secuirty Researcher
As a Staff AI Security Researcher, you will be tasked with leading efforts identifying and understanding security risks unique to AI systems. Investigate demonstrate attacks - prompt injections, jailbreaks, data leakage, agentic workflow hijacking and architecture/ecosystem flaws (plugins, connectors, MCPs, skills). Translate findings into detections and safeguards, and help build our agentic detection and response capabilities from the ground up.
What Will You Do?
Primary responsibilities include:
Conduct advanced research to identify vulnerabilities within AI (LLMs, SLMs) models, agentic systems and their infrastructure, including prompt injection, jailbreaking, data exfiltration, and misuse vectors.
Build threat models for emerging AI capabilities and deployment surfaces (agents, tool use, multimodal systems).
Innovate and design novel methodologies and automated tools to systematically and continuously probe AI security mechanisms at scale.
Partner with engineering and product teams to translate research findings into our Agentic Detection and Response offering.
Stay informed on the latest academic, industry and threat landscape trends on adversarial ML, agentic and AI security.
Mentor other researchers and engineers and help grow the team's technical capabilities.
Publish research findings internally and externally through papers, blog posts, or industry conferences.
What Skills and Knowledge Will You Bring?
Ideal candidates will have:
6+ years of experience in offensive research, red teaming or pentesting, with focus on AppSec or Identity.
Hands-on experience with adversarial techniques against AI (LLMs, SLMs) and ML systems - prompt injection, jailbreaking, membership inference, model extraction, data poisoning, etc.
Good understanding of identity/access management (IAM) protocols and tools.
Familiarity with agentic attack taxonomies such as OWASP Top 10 for LLMs and MITRE ATLAS.
Proficiency in programming and scripting languages (Python, JavaScript and Java) and Cloud environments (AWS, GCP, Azure, Kubernetes).
Technical writing & content development skills.
Publication record or demonstrable body of work in security research, adversarial ML, or AI safety (papers, disclosed vulnerabilities, open-source tools, etc.) - advantage.
Experience in leading cross-functional technical initiatives - advantage.
Why SentinelOne?
AI is redefining how the world operates and rewriting the rules of security in real time, and SentinelOne was built for this moment. From day one, we architected an AI-native platform designed to operate at machine speed, not as an add-on to legacy systems but as the foundation itself. If you want to build where innovation and impact move together, this is that place.
We invest in our Sentinels with comprehensive, competitive benefits designed to support you and your family:
Equity & Rewards
Restricted Stock Units (RSUs)
Employee Stock Purchase Plan (ESPP)
Time Off & Wellbeing
Competitive leave benefits
Gender-neutral parental leave
Employee Assistant Program
Workout sessions and a Wellness App
Insurance & Financial Security
Medical and insurance benefits
Pension
Employee Assistance Program (EAP)
Work Perks & Flexibility
Global home office allowance
Mobile phone reimbursement
Study Fund