Principal Researcher, AI Red Teaming (Remote, ITA)

CrowdStrike Inc.; Asti; À distance; EUR 140 000 - 210 000; Plein temps

Avantages offerts par ce poste

Market leader in compensation and fine

Comprehensive wellness programs

Professional development opportunities

Résumé du poste

CrowdStrike Inc. cerca un Principal Researcher per guidare l’agenda di red-teaming AI e guidare ricerche ad alto impatto sul platform di sicurezza AI. Il ruolo richiede leadership tecnica, capacità di coordinare tra ingegneria, prodotto e legale, e di discutere disclosure credibili e robuste.

La posizione richiede competenze avanzate in sicurezza offensiva, ricerca su LLM e sistemi agentici, con una forte abilità comunicativa scritta per report esterni e disclosure.

Qualifications

• Pubblici record di ricerche originali nel campo della sicurezza (CVEs, disclosure, talk o paper).
• Esperienza pratica offensiva pesante (exploit, vulnerability research, red teaming).
• Ricerca dimostrata su LLM o sistemi agentici (prompt/instrumentation, attacchi multi-agent).
• Ottima padronanza di Python e ingegneria di sistemi (harnesses, interceptors, converters).
• Comprensione del design di sistemi agentici (uso di strumenti, loop di pianificazione, memoria, sandboxing).
• Capacità di definire direzione tecnica per team di ricercatori.

Responsabilités

• Definire e dare priorità a classi di attacco, bersagli e comportamenti di frontier-model con motivazioni e scadenze.
• Red team di modelli frontier e sistemi agentici; monitorare l’impatto delle release sugli attacchi, sul comportamento e sui controlli.
• Conduzione di ricerche di vulnerabilità end-to-end in ecosistemi agentici.
• Produrre note di ricerca all’avanguardia, paper esterni, talk e disclosure coordinate.
• Indagare failure modes in sistemi multi-agente e compiti a lungo termine.
• Progettare e implementare tooling per ricerca e red-teaming (attack harnesses, interceptors, converters).
• Convertire i risultati in moduli di attacco riutilizzabili per la piattaforma di sicurezza AI.
• Fornire linee guida tecniche su agenda di ricerca esterna, disclosures e collaborazioni.
• Comunicare chiaramente rischi e scoperte a ingegneria, product owner, legale ed esecutivi.
• Revisionare disclosures, classi di attacco e lab designs come reviewer tecnico finale

Connaissances

Python

Red Teaming

LLMs research

Agentic systems

Leadership

Outils

Harnesses

Interceptors

Converters

Description du poste

Overview

As 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.

Retribuzione / Benefits

• 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

Responsabilità

• Define and prioritise attack classes, agent targets, and frontier-model behaviours with rationale and deadlines
• Red team frontier models and agentic systems; track impact of model releases on attacks, behaviour, and controls
• Conduct end-to-end vulnerability research and security assessments of agentic ecosystems
• Produce state-of-the-art research notes, external papers, talks, and coordinated disclosures
• Investigate failure modes in multi-agent systems and long-horizon tasks
• Design and implement tooling for research and red-teaming (attack harnesses, interceptors, converters)
• Convert findings into reusable attack modules for the automated AI security testing platform
• Provide technical guidance on external research agenda, disclosures, and collaborations
• Communicate findings and risk clearly to engineering, product owners, legal, and executives
• Review disclosures, attack classes, and lab designs as final technical reviewer

Requisiti fondamentali

• Public record of original security research (CVEs, coordinated disclosures, talks, or papers)
• Deep hands-on offensive security expertise (exploitation, vulnerability research, red teaming)
• Demonstrated research on LLMs or agentic systems (prompt/instrumentation techniques, multi-agent attacks)
• Strong Python and systems engineering skills (harnesses, interceptors, converters)
• Understanding of agentic systems design (tool use, planning loops, memory, sandboxing, trust boundaries)
• Experience setting technical direction for researchers as a tech lead or principal
• Exceptional written communication for external-facing notes and disclosures

• Exceptional written communication
• Ability to set technical direction and influence peers
• Strong problem-solving and investigative mindset
• Python
• systems engineering
• offensive security and vulnerability research