Staff AI Secuirty Researcher
About this role
SentinelOne needs to proactively identify and mitigate complex security risks unique to evolving artificial intelligence systems and infrastructure. To address this challenge, the organization is hiring a Staff AI Security Researcher to lead advanced offensive research and build robust safeguards from the ground up.
In this capacity, the specialist will investigate sophisticated attack vectors such as prompt injections, jailbreaks, data leakage, and agentic workflow hijacking. The mandate involves building threat models for emerging AI capabilities, designing automated tools to probe security mechanisms at scale, and translating research findings into the company's Agentic Detection and Response offering.
Candidates who thrive in this environment are relentlessly curious, committed to continuous learning, and capable of operating at the intersection of AI and security. A successful hire will combine deep technical expertise in adversarial machine learning with a strong background in offensive security, identity protocols, and cloud environments.
What you will do
- Conduct advanced research to identify vulnerabilities within large language models, small language models, agentic systems, and their underlying infrastructure.
- Build comprehensive threat models for emerging AI capabilities and deployment surfaces including agents, tool use, and multimodal systems.
- Innovate and design novel methodologies and automated tools to systematically and continuously probe AI security mechanisms at scale.
- Partner closely with engineering and product teams to translate research findings directly into the Agentic Detection and Response offering.
- Stay informed on the latest academic, industry, and threat landscape trends related to adversarial machine learning and AI security.
- Mentor other researchers and engineers to help grow the team's overall technical capabilities.
- Publish research findings both internally and externally through papers, blog posts, or industry conferences.
What you need
- Bring six or more years of experience in offensive research, red teaming, or penetration testing with a focus on application security or identity.
- Possess hands-on experience applying adversarial techniques against artificial intelligence and machine learning systems such as prompt injection, jailbreaking, and data poisoning.
- Demonstrate a good understanding of identity and access management protocols and tools.
- Show familiarity with agentic attack taxonomies including the OWASP Top 10 for LLMs and MITRE ATLAS.
- Demonstrate proficiency in programming and scripting languages like Python, JavaScript, and Java, alongside cloud environments including AWS, GCP, Azure, and Kubernetes.
- Possess technical writing and content development skills.
Nice to have
- Publication record or demonstrable body of work in security research, adversarial ML, or AI safety
- Experience in leading cross-functional technical initiatives
Benefits
- Restricted Stock Units and Employee Stock Purchase Plan
- Competitive leave benefits and gender-neutral parental leave
- Employee Assistant Program, workout sessions, and a Wellness App
- Medical and insurance benefits plus pension
- Global home office allowance, mobile phone reimbursement, and study fund
Skills and tech stack
Questions candidates ask
What will I actually work on in this role?
You will lead efforts to identify security risks unique to AI systems by investigating attacks like prompt injections, jailbreaks, data leakage, and agentic workflow hijacking. Your findings will be translated into detections and safeguards to help build agentic detection and response capabilities from the ground up.
What are the core technical requirements for applicants?
Ideal candidates need six or more years of experience in offensive research, red teaming, or pentesting with a focus on AppSec or Identity. You must also have hands-on experience with adversarial techniques against AI and ML systems, familiarity with frameworks like OWASP Top 10 for LLMs and MITRE ATLAS, and proficiency in Python, JavaScript, Java, and cloud environments.
What perks and benefits are provided?
The company invests in employees through comprehensive benefits that include restricted stock units, an employee stock purchase plan, competitive leave benefits, and gender-neutral parental leave. Additional perks include medical and insurance coverage, a pension, a global home office allowance, mobile phone reimbursement, and a study fund.