…Threat Exposure Management (CTEM). The HackerOne Platform unites agentic AI solutions with the ingenuity of the world’s largest community of security researchers to…

…security, including threats to AI systems, adversarial machine learning, prompt injection, or AI supply chain security - - Experience applying AI to security work, including agentic…

…tooling the security pillar teams operate on, moving security operations from manual triage to correlation-based detection, automated response, and agentic AI. The team…

…tooling the security pillar teams operate on, moving security operations from manual triage to correlation-based detection, automated response, and agentic AI. The team…

…By combining a battle-tested hyperautomation engine with agentic AI, Torq lets security teams triage, investigate, and respond to threats at machine speed — moving…

…Experience performing threat modeling, security reviews, red teaming, adversarial testing, or incident response. Familiarity with AI safety, AI security research, or emerging attack and…

…tooling the security pillar teams operate on, moving security operations from manual triage to correlation-based detection, automated response, and agentic AI. The team…

…Threat Exposure Management (CTEM). The HackerOne Platform unites agentic AI solutions with the ingenuity of the world’s largest community of security researchers to…

…By combining a battle-tested hyperautomation engine with agentic AI, Torq lets security teams triage, investigate, and respond to threats at machine speed — moving…

…AI or GenAI workflows (for example Cortex AI) to security analysis, detection, or automation - Contributions to open-source security projects or published security research…

…user research at scale, and designers rapidly prototyping and iterating with AI-generated mockups. We approach AI the same way we approach security: with…

…Principal Security Research Manager on the AI Evaluation Systems team, you will build the common evaluation platform and methodology used by MSec agent programs…

…engineering, and AI, partnering with threat researchers, data scientists, and engineers, and evangelizing our approach to a global community of security practitioners. What You…

…Threat Exposure Management (CTEM). The HackerOne Platform unites agentic AI solutions with the ingenuity of the world’s largest community of security researchers to…

…come up with new security posture insights. Build and evaluate AI-for-Research-Productivity and AI-in-Production agentic workflows. Work together with the…

…s security posture focusing on AI, Agents, harnesses and LLM’s. Key Responsibilities: AI Security and Vulnerability Research: Stay current with emerging threats and…

…debugging, security research, testing, and documentation. We also empower engineers to go beyond personal productivity by building AI-powered tools and agents that improve…

…frontier AI systems. 2. Mitigation. Keeping misuse and misalignment safeguards, alignment tools, and security measures on track to adequately address extreme threats that might…

…Built capability-based or ownership-based security models for low-level systems. Built security automation, fuzzing infrastructure, review agents, or AI-assisted tools used…

…you have already done work in one of the domains listed above (ML research, AI alignment, AI verification etc). About OpenAI OpenAI is an…

…Strong understanding of AI/ML security adversarial machine learning, model security, threat modeling, secure MLOps — and familiarity with encryption and secure system design. Demonstrated…

…Modern models can autonomously discover vulnerabilities, chain exploits across multiple systems, manipulate agents through prompt injection, and escape “secure” containment. AI safety is extremely…

…By delivering hardened, secure, and production-ready builds of all the open source software engineers and AI agents rely on, Chainguard helps organizations build…

…Microsoft Security Research is at the front line of defending Microsoft customers and the broader ecosystem against the world's most sophisticated threat actors…

…You are excited rather than intimidated by the security challenges unique to autonomous agents and AI-native developer tools. - Relevant industry experience: Prior experience…