Red Team Tech Lead
About Us:
Zenity is the leading AI agent security company, helping enterprises secure AI agents everywhere, from SaaS and cloud to the endpoint. Our research team is among the most respected in the field, uncovering real-world attack paths against AI agents and shaping how the industry thinks about agentic threats.
About the Role:
We’re looking for a Red Team Tech Lead to be a close partner to our Director of Red Team, and a senior technical voice and leader for Zenity’s research, inside the company and out in the community.
This is a deeply hands-on role. You’ll lead by doing: conducting original research, building proofs of concept, and breaking the newest AI technologies out there, all while owning the connective tissue between the research team and the rest of the company. You’ll step into end-to-end research and product conversations, represent the team in cross-functional and leadership forums, and turn the team’s work into impact, from first hypothesis to a published finding and a shipped product capability.
Our field reinvents itself every few months. A year ago the conversation was about prompt injection; today the attack paths, the platforms, and the questions are entirely different. We need someone who thrives in that constant change and sees where it’s heading before everyone else does.
This is a leadership position without direct reports. You’ll drive a team of strong researchers through technical credibility and influence, not org charts.
Responsibilities:
- Lead research end to end. Shape research direction, drive projects from idea to execution, and make sure the team’s work lands with depth and rigor.
- Partner with the Director of Red Team. Represent the Red Team in cross-functional forums, product discussions, and senior-peer conversations.
- Bridge vision and execution. Translate the team’s goals into concrete plans, keep momentum, and push the group forward on delivery.
- Connect research to the business. Work with senior peers across Product, Engineering, and Marketing to turn the team’s outputs into product capabilities, content, and customer value.
- Stay deeply technical in research. Go deep on AI agent security: understand how agents work, where and why they break, know the Zenity platform well, and run your own original research.
- See the shift before it happens. Understand how AI is changing the security model, anticipate where it’s going, and demonstrate it in new and compelling ways every time.
- Break platforms and read the market. Hack and take apart AI platforms, study the product category as a whole, and work out where it’s heading and which problems are coming before they arrive.
- Rethink the attack surface. Think creatively about the attack surface that AI creates and how it keeps evolving, and turn that thinking into research direction.
- Be Zenity’s voice in the community. Present at leading security conferences such as Black Hat and DEF CON, represent our research publicly, and handle the Q&A, press, and technical deep-dives that come with being the face of our findings.
- Be a researcher the team trusts. Earn the respect of the team through research depth, sound judgment, and curiosity.
Requirements:
- 8+ years in offensive security, vulnerability research, or red teaming, including 3+ years leading technical work or projects.
- Deep, demonstrable expertise in AI security. You understand how AI systems and agents work, how they fail, and how they’re attacked.
- Strong hands-on research depth: you conduct original, technically rigorous research yourself and take it from first idea to published finding.
- Strategic vision: the ability to see how AI reshapes security models and product categories before the change is obvious.
- A proven record of technical leadership: you drive people and projects through credibility.
- Experience speaking at major security conferences and representing research publicly. You’re comfortable on stage and in front of tough technical questions.
- A public footprint in the security research community, such as talks, publications, CVEs, or open-source work.
- Excellent communication skills in English and Hebrew, moving easily between deep technical detail and executive-level framing.
- Willingness to travel internationally for conferences.
Nice to have
- Experience building or growing a research brand or program.
- Experience breaking or reverse engineering AI and agent-building platforms.
You’ll join a Series C company at the center of one of the fastest-moving areas in security, work alongside a world-class research team, and have real influence on how the industry thinks about AI agent security, with a clear path to broader leadership as the team grows.
Required Languages
🇬🇧 English, 🇮🇱 HE