Principal Researcher, AI Red Teaming (Remote, ITA)
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. /pulliMarket leader in compensation and equity awards /liliComprehensive physical and mental wellness programs /liliCompetitive vacation and holidays for recharge /liliPaid parental and adoption leaves /liliProfessional development opportunities for all employees regardless of level or role /liliEmployee Networks, geographic neighborhood groups, and volunteer opportunities to build connections /liliDefine and prioritise attack classes, agent targets, and frontier-model behaviours with rationale and deadlines /liliRed team frontier models and agentic systems; track impact of model releases on attacks, behaviour, and controls /liliConduct end-to-end vulnerability research and security assessments of agentic ecosystems /liliProduce state-of-the-art research notes, external papers, talks,
and coordinated disclosures /liliInvestigate failure modes in multi-agent systems and long‑horizon tasks /liliDesign and implement tooling for research and red‑teaming (attack harnesses, interceptors, converters) /liliConvert findings into reusable attack modules for the automated AI security testing platform /liliProvide technical guidance on external research agenda, disclosures, and collaborations /liliCommunicate findings and risk clearly to engineering, product owners, legal, and executives /liliReview disclosures, attack classes, and lab designs as final technical reviewer /liliPublic record of original security research (CVEs, coordinated disclosures, talks, or papers) /liliDeep hands‑on offensive security expertise (exploitation, vulnerability research, red teaming) /liliDemonstrated research on LLMs or agentic systems (prompt/instrumentation techniques, multi‑agent attacks) /liliStrong Python and systems engineering skills (harnesses, interceptors, converters) /liliUnderstanding of agentic systems design (tool use, planning loops, memory, sandboxing, trust boundaries) /liliExperience setting technical direction for researchers as a tech lead or principal /liliExceptional written communication for external-facing notes and disclosures /li /ulpAs Principal Researcher, you set the strategic AI red‑teaming agenda and execute the hardest research yourself to advance CrowdStrike’s AI s… /p #J-18808-Ljbffr
and coordinated disclosures /liliInvestigate failure modes in multi-agent systems and long‑horizon tasks /liliDesign and implement tooling for research and red‑teaming (attack harnesses, interceptors, converters) /liliConvert findings into reusable attack modules for the automated AI security testing platform /liliProvide technical guidance on external research agenda, disclosures, and collaborations /liliCommunicate findings and risk clearly to engineering, product owners, legal, and executives /liliReview disclosures, attack classes, and lab designs as final technical reviewer /liliPublic record of original security research (CVEs, coordinated disclosures, talks, or papers) /liliDeep hands‑on offensive security expertise (exploitation, vulnerability research, red teaming) /liliDemonstrated research on LLMs or agentic systems (prompt/instrumentation techniques, multi‑agent attacks) /liliStrong Python and systems engineering skills (harnesses, interceptors, converters) /liliUnderstanding of agentic systems design (tool use, planning loops, memory, sandboxing, trust boundaries) /liliExperience setting technical direction for researchers as a tech lead or principal /liliExceptional written communication for external-facing notes and disclosures /li /ulpAs Principal Researcher, you set the strategic AI red‑teaming agenda and execute the hardest research yourself to advance CrowdStrike’s AI s… /p #J-18808-Ljbffr