h3Overview /h3 pAs Principal Researcher, you set the strategic AI red-teaming agenda and execute the hardest research yourself to advance CrowdStrike's AI security platform. You lead frontier-model investigations, build repeatable tooling, and raise the bar for peers, shaping disclosures and reusable attack modules. You work across engineering, product, and legal to ensure findings are actionable and publicly credible. This role combines deep technical leadership with high-impact, mission-driven research in AI safety. /p h3Retribuzione / Benefits /h3 ul liMarket leader in compensation and equity awards /li liComprehensive physical and mental wellness programs /li liCompetitive vacation and holidays for recharge /li liPaid parental and adoption leaves /li liProfessional development opportunities for all employees regardless of level or role /li liEmployee Networks, geographic neighborhood groups, and volunteer opportunities to build connections /li /ul h3Responsabilità /h3 ul liDefine and prioritise attack classes, agent targets, and frontier-model behaviours with rationale and deadlines /li liRed team frontier models and agentic systems; track impact of model releases on attacks, behaviour, and controls /li liConduct end-to-end vulnerability research and security assessments of agentic ecosystems /li liProduce state-of-the-art research notes, external papers, talks,



and coordinated disclosures /li liInvestigate failure modes in multi-agent systems and long-horizon tasks /li liDesign and implement tooling for research and red-teaming (attack harnesses, interceptors, converters) /li liConvert findings into reusable attack modules for the automated AI security testing platform /li liProvide technical guidance on external research agenda, disclosures, and collaborations /li liCommunicate findings and risk clearly to engineering, product owners, legal, and executives /li liReview disclosures, attack classes, and lab designs as final technical reviewer /li /ul h3Requisiti fondamentali /h3 ul liPublic record of original security research (CVEs, coordinated disclosures, talks, or papers) /li liDeep hands-on offensive security expertise (exploitation, vulnerability research, red teaming) /li liDemonstrated research on LLMs or agentic systems (prompt/instrumentation techniques, multi-agent attacks) /li liStrong Python and systems engineering skills (harnesses, interceptors, converters) /li liUnderstanding of agentic systems design (tool use, planning loops, memory, sandboxing, trust boundaries) /li liExperience setting technical direction for researchers as a tech lead or principal /li liExceptional written communication for external-facing notes and disclosures /li /ul ul liExceptional written communication /li liAbility to set technical direction and influence peers /li liStrong problem-solving and investigative mindset /li liPython /li lisystems engineering /li lioffensive security and vulnerability research /li /ul #J-18808-Ljbffr

📌 Principal Researcher, AI Red Teaming (Toscana)
🏢 CrowdStrike
📍 Toscana