SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 230,000 - 280,000 / annual
Gray Swan is building the infrastructure to evaluate and secure frontier AI systems against cyber threats. This role leads the company's cyber safety capability from the ground up, serving as the technical authority on AI-enabled cyber risk across red-teaming, evaluation, benchmarking, defenses, and safety infrastructure.
You will design and lead adversarial evaluations of frontier large language models for offensive cyber capabilities, including vulnerability discovery, exploit development, malware generation, privilege escalation, social engineering, persistence, and autonomous cyber operations. You'll partner closely with machine learning engineers to translate deep cybersecurity expertise into scalable benchmarks, classifiers, guardrails, automated detection systems, and evaluation infrastructure for both internal products and frontier AI lab deployments.
Key responsibilities include developing and maintaining Gray Swan's catastrophic cyber harm taxonomy, producing technical risk assessments and actionable recommendations for frontier AI labs and enterprise customers, and building and mentoring a world-class team of cybersecurity subject matter experts. You'll represent Gray Swan as the company's cybersecurity authority, collaborating with frontier AI labs, security researchers, government partners, and the broader AI safety and cybersecurity communities.
You bring deep technical expertise in offensive cybersecurity, vulnerability research, exploit development, penetration testing, malware analysis, or reverse engineering. You have significant experience assessing advanced cyber threats and AI-enabled cyber capabilities, particularly in critical infrastructure. Hands-on experience conducting adversarial evaluations, AI red-teaming, or LLM security research is essential. You thrive in ambiguous, fast-moving environments and are a builder who enjoys creating teams and infrastructure from scratch. Experience with machine learning models, frontier model red-teaming, national security organizations, or threat intelligence is a plus.
