Head of AI Safety & Security Research/ Director of AI Research
About the Position
You will define Alice's research agenda in AI safety, security, and model evaluation - and drive the science that delivers it. The benchmarks you design will become the new world-standards. The methods you develop will run inside the labs defining what AI becomes.
Specifically, the org you will be leading technically, is Alice Labs, that includes AI researchers from across Alice departments and directly within the Alice Labs department.
This is a role for someone whose strength is in scientific pragmatism. Pushing the envelope on how new frontier research should apply to AI safety and security.
You will ship three new benchmarks/evals every month, one breakthrough benchmark each quarter, and at least one paper per quarter at top-tier conferences (eg. NeurIPS, ICML, ICLR, ACL, or IEEE S&P etc)
You will also represent Alice externally - at conferences and events, with research partners, and on visits to frontier labs. Travel is an important part of this role: it is how science stays sharp and how Alice stays at the frontier.
What you will own
- The research roadmap - safety, security, red teaming, adversarial robustness, LLMs, agents, and multimodal systems and more.
- Benchmark and evaluation design - frameworks and methods that surface real vulnerabilities in frontier models
- Research relationships with leading frontier labs and academic institutions
- Collaborative engagements with technical teams at partner organizations
- Alice's published research output and scientific reputation
- The pipeline from research to product - working with engineering and product to ship findings at scale
Requirements
- A research leader whose primary strength is scientific, yet pragmatic and grounded in the real needs of the future - someone who has worked at the frontier and wants to push it further
- Deep expertise in AI safety, security, red teaming, or adversarial robustness
- A strong publication record at leading AI or security venues
- Experience mentoring or leading senior researchers
- Comfort engaging with technical partners and collaborators
- Willingness to travel, including internationally
- PhD in AI, ML, CS, or security is a strong advantage - a compelling research record without one is equally welcome
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.