Senior GenAI Analyst
About the Position
At Alice, GenAI Analysts test AI systems against emerging threats. This role sits between red teaming and research. You follow frontier AI risks, model releases, regulation and the news cycle closely. When something new happens, whether a headline, a law, or a shift in how people use AI, your first questions are how it could be misused and how to test for it.
You’ll turn those developments into well-scoped red teaming scenarios, map them to major AI products, and keep testing grounded in real-world risk, including in areas where policy is still taking shape.
What you'll do
- Adversarial Testing: Design and run adversarial tests across a wide range of AI systems: text, image, video and multimodal models, as well as emerging modalities like text-to-3D and physical AI. This includes jailbreaks and adversarial prompts, along with new testing approaches suited to each system. Build test datasets, and use scripts or tooling to scale them.Craft and execute jailbreaks, adversarial prompts, and automated test datasets across text, image, video, and multimodal LLMs.
- Threat Ideation: Track frontier AI risks, news, and regulations and turn them into structured red teaming scenarios.
- Product and policy mapping: Connect real-world risks to specific AI products and features. Make sure testing reflects how products are actually used and helps inform policy where it’s still being defined.
- Methodology and quality: Help the team design testing methodologies, and review deliverables to make sure they meet quality standards.
Requirements
Must have
- Located in Israel
- Near-native English
- Background in AI Safety, responsible AI, trust and safety, or AI ethics.
- Strong, ongoing awareness of frontier AI risks, current events, and AI laws and regulation.
- Proven ability to turn news and trends into structured, testable red teaming ideas.
- Hands-on familiarity with current generative AI models and agents. Direct technical experience is not a prerequisite.
- Strong attention to detail and organization. Comfortable running several workstreams at once. Experience designing test methodologies or reviewing others’ work for quality.
Nice to have
- Experience testing different model types (text, image, multimodal, 3D or physical AI).
- Research experience, for example on academic projects.
- A self-starter who does well in a fast-moving and changing environment.
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.