Principal Researcher, AI Red Teaming

• Set the technical direction and research agenda for AI red teaming as an individual contributor
• Propose and prioritise attack classes, agent target classes and frontier model behaviours for study
• Red team frontier models and agentic systems, tracking attack success, agent behaviour and effective controls
• Conduct end-to-end vulnerability research and security assessments on agentic ecosystems
• Produce internal research notes, external papers, conference talks and coordinated disclosures
• Investigate difficult failure modes in multi-agent systems, long-horizon tasks and apparently effective defences
• Design and write attack harnesses, action-trace capture systems, tool-call interception, payload converters, isolated lab targets and reproducible experiment runners
• Convert findings into reusable attack modules for the automated AI security testing platform
• Define shared formats for attack content and action traces
• Own the external research agenda, including venues, disclosures, collaborations and quality standards
• Review benchmark methodology and research findings for attacker realism and evidence quality
• Communicate findings, limitations and risks to engineering, product owners, legal and executives
• Serve as final technical reviewer for disclosures, attack classes and lab design

• A substantial and verifiable public record of original security research, including CVEs, coordinated disclosures, conference talks or peer-reviewed papers led by the candidate
• Deep hands-on expertise in offensive security, including exploitation, vulnerability research or red teaming
• Demonstrated research on LLMs or agentic systems, including prompt and environment injection, tool-use abuse, jailbreaks, multi-agent attacks, or adversarial model evaluation; shareable artifacts required
• Strong Python and systems engineering skills
• Practical understanding of agentic systems, including tool use, planning loops, MCP, memory, sandboxing, and trust boundaries
• Experience setting technical direction for other researchers as a tech lead or principal, with evidence of developing others into leaders
• Exceptional written communication
• Published research on AI security, agent security or adversarial machine learning at recognised venues is a bonus
• Experience red teaming frontier models directly or working with frontier model providers on disclosures is a bonus
• Patents or shipped tooling in automated red teaming, agent evaluation or security testing is a bonus
• Experience with isolated lab design, including sandboxing, egress control, C2 sinkholes and telemetry retention, is a bonus

• Market leader in compensation and equity awards
• Comprehensive physical and mental wellness programs
• Competitive vacation and holidays for recharge
• Paid parental and adoption leaves
• Professional development opportunities for all employees regardless of level or role
• Employee Networks, geographic neighborhood groups, and volunteer opportunities to build connections
• Vibrant office culture with world class amenities
• Great Place to Work Certified™ across the globe
• Additional bonus/commission pay
• Comprehensive benefits package including medical and dental insurance
• Access to Modern Health wellbeing resources
• Life and disability coverage