AI Researcher at Irregular (Tel Aviv, Israel)
Irregular· Tel Aviv, Israel·
Role details
Job description
About Irregular
Irregular is the first frontier security lab with the mission of protecting the world in the time of increasingly capable and sophisticated AI systems. We build next-generation defenses through high-fidelity research platforms that simulate and monitor real-world AI security scenarios. As AI systems become more powerful, we focus on staying ahead of emerging threats and vulnerabilities, ensuring these transformative technologies can be deployed safely and securely.
About the Role
As an AI researcher at Irregular, you'll be at the forefront of researching advanced frontier model capabilities and agent behavior, and help shape the future of AI security evaluation and mitigation. In this role, you will advance the frontier knowledge of AI and agentic frameworks, methods of assessing their ability, and mitigations for dangerous capabilities.
Representative projects:
- Researching capability elicitation methods to enhance model performance in evaluations.
- Researching methodologies to assess generalization and coverage in model capabilities evaluation frameworks.
- Contributing to academic publications and delivering research findings to customers.
- Creating unique solutions to mitigate scenarios of AI loss of control or misalignment.
- Advising and supporting the development of the products we’re building.
You may be a good fit if you:
- Have a strong research experience in machine learning, particularly with frontier AI models.
- Can design and implement novel research approaches for emerging AI challenges.
- Work well in a multidisciplinary team and can adapt to rapidly evolving research questions.
- Have a track record of publishing peer-reviewed research in top-tier venues (e.g., AAAI, ACL, EMNLP, ICLR, ICML, Nature, NeurIPS, Science, or similar).
- Care about the societal impacts of your work.
Why work at Irregular
- Mission-driven work: The opportunity to work on what the founders describe as “the defining problems of AI security” and to build the defenses that will keep advanced AI secure for the world.
- Elite, talent-dense team: Work alongside AI scientists, top cyber experts, and senior leaders from the world’s most prestigious institutions. The culture emphasizes curiosity, high standards, and intellectual rigor.
- Resources & backing: Backed by top-tier investors (Sequoia, Redpoint) with significant funding ($80M), and already profitable, providing strong stability and runway.
- Work policy: Hybrid workspace in Tel Aviv, Israel. Most roles are listed as “In-Office” or hybrid with a typical expectation of on-site presence.
- Hiring process: A structured, multi-stage process designed to reduce bias and allow candidates to showcase their strengths. Stages include an exploratory chat, a take-home assignment (approx. 5 hours) or online interview, a day of 2-3 technical interviews, and a leadership fit interview. The company is committed to moving swiftly and accommodating candidate timelines.