Jobs at Alice (Formerly ActiveFence)

Evaluate and red-team generative AI systems for biological safety and dual-use risks. Apply expertise in biosecurity, biosafety, pathogens, genetic modification, toxins, and biomanufacturing to develop actionable model-safety feedback. Monitor emerging biotechnology and governance developments, update safety benchmarks, assess LLM outputs, and communicate complex biological risks to AI safety and alignment teams.

Evaluate and strengthen Generative AI safety guardrails for chemical information. Conduct adversarial red-teaming, taxonomy audits, prompt research, and model evaluations to identify dual-use risks and prevent chemical harm enablement. Assess toxicological accuracy, clandestine synthesis content, and regulatory compliance. Document findings, rank risks, and communicate recommendations to safety and alignment teams while maintaining expertise in chemical conventions, precursor controls, and industrial safety standards.

Lead AI safety research across generative AI models, multimodal systems, and AI agents. Design scalable evaluation and red-teaming methodologies, investigate jailbreaks and prompt injection, assess content safety risks, manage multilingual datasets, document research findings, mentor junior researchers, and communicate mitigation recommendations to engineering, product, policy, and client teams.

Analyze generative AI content infringements and develop adversarial prompts to identify model vulnerabilities across hate speech, misinformation, intellectual property, and other abuse areas. Manage multilingual datasets, investigate safety circumvention tactics, oversee projects and quality assurance, and collaborate with engineering, product, and policy teams to improve AI safety strategies.

Conduct adversarial red-teaming of generative AI models against cyber-CBRNE threats. Design jailbreaks, adversarial prompts, multi-turn attacks, and scenario evaluations; assess safeguard bypasses and dangerous capability escalation; develop attack scenarios involving ICS, OT, critical infrastructure, laboratories, and hazardous facilities; document failure modes, reproduce vulnerabilities, classify severity, and recommend mitigations. Build repeatable test suites, adversarial datasets, evaluation rubrics, and risk taxonomies while tracking emerging AI security, cyber threat, and CBRNE risks.

Lead a multidisciplinary red teaming team to design and run adversarial tests, evaluate model risks, produce high-quality deliverables, and communicate findings to clients while improving methodologies and workflows.

Lead AI safety role developing adversarial prompt strategies, owning end-to-end projects, mentoring junior analysts, managing multilingual abuse datasets, researching circumvention tactics, and partnering with engineering, product, and policy teams to secure generative AI models.

Analyze content infringements and write adversarial prompts to find model vulnerabilities across LLMs, text-to-image/video, and agents. Manage datasets and projects end-to-end, investigate evasion tactics, collaborate with engineering, product, and policy teams, and promote knowledge sharing to improve model safety.