Senior GenAI Safety Researcher: Frontier Risk
About the Position
Alice.io is seeking a Senior Researcher to drive research execution and technical delivery across frontier AI risks, with a focus on CBRNE and cybersecurity threat vectors.
Reporting directly to a Team Lead, you will serve as the strategic nexus connecting client partners, domain specialists, and our core analysis team. You will lead client-facing engagements, translating intricate multimodal threat landscapes into actionable mitigation frameworks for client engineering and safety leadership.
Key Responsibilities
- Lead the execution of red-teaming datasets, evaluation protocols, and technical risk reports; institute QA checkpoints across base-model, guardrail, and agentic workflows across text, vision, and audio modalities.
- Model bandwidth, allocate tasks across subject-matter expert pools (including PhD-level researchers), and maintain delivery velocity under compressed client deadlines.
- Conduct rigorous technical and methodological reviews on all analytic outputs to ensure findings are defensible, reproducible, and aligned with dual-use containment standards.
- Serve as the primary analytical lead in client meetings, presenting threat modeling, residual risk levels, and architecture-level mitigations to external engineering leads.
- Monitor emerging frontier capabilities to refine Alice’s internal CBRNE and cyber evaluation frameworks against state-of-the-art dual-use risks.
Requirements
Must Have
- 2–4 years of experience spanning AI safety, red-teaming, CBRNE risk, or cyber threat intelligence.
- Proven ability to drive complex technical projects and align specialized experts against demanding deadlines.
- Sound technical judgment when navigating dual-use risks, hazardous materials, and sensitive cyber vulnerabilities.
- Clear, persuasive communication skills, with ease translating high-stakes risk architectures for engineering and executive leadership.
Nice to Have
- Advanced degree in chemistry, biology, nuclear science, computer security, or AI.
- Offensive security experience (pen testing, vulnerability research, CTFs).
- In-depth understanding of frontier AI evaluation benchmarks, capability threshold triggers, and lab preparedness frameworks.
About Alice
THE CHALLENGES ALONG THE WAY
1. Being Both Strategist and Executioner
One of the hardest parts of this role is that you’re both the visionary and the builder; the one drawing the map and paving the road.
That means switching between high-level strategy and hands-on experimentation daily, and doing it while bringing others along with you. There’s no playbook for this kind of work. You’re paving an unpaved road, one small experiment at a time.
2. Balancing Security and Innovation
ActiveFence is the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the world’s largest enterprises and tech platforms every day.
As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.