--- title: 'Research Engineer at Irregular' canonical: 'https://feeny.ai/job/research-engineer-irregular-tel-aviv-kcny5xf1bfh7' type: 'job' last_seen: '2026-09-10' --- # Research Engineer at Irregular - **Company:** Irregular - **Location:** Tel Aviv, Israel - **Employment:** full-time - **Work type:** onsite - **Posted:** 2026-06-10 - **Last confirmed live:** 2026-09-10 - **Apply:** https://jobs.ashbyhq.com/irregular/7e8a2432-0ed7-4fd7-8bcd-d0d89db663b3 ## 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 a research engineer at Irregular, you'll be at the forefront of building systems to evaluate and secure frontier AI models. You'll work on infrastructure and experiments to assess model capabilities, implement agent frameworks, and develop mitigations for advanced AI systems. Your role will involve creating robust evaluation pipelines, developing security-focused testing frameworks, and building tools that help understand and mitigate risks related to frontier models. You’ll have a chance to understand the research context and your code’s impact and contribute as a meaningful part of a growing team. Representative projects: - Building a tool to continuously evaluate models and mitigate their risks. From designing the APIs for frontier labs, to building analysis and visualization tools that summarize 10,000+ transcripts into specific conclusions. - Designing and building challenges that measure a model’s ability to evade discovery, allowing us to see if models can operate on remote systems while avoiding detection by common defensive security tools. - Developing controlled environment frameworks for more secure use of frontier models. - Designing and building agents that improve a model’s ability to complete complex tasks. Includes many potential avenues, such as incorporating SOTA prompting practices, creating tools for task delegation, and more. - Publishing your research and/or delivering research to our customers. You may be a good fit if you: - Have strong production programming skills and experience. - Have strong problem-solving and analytical skills. - Work well in a multidisciplinary team and can adapt to rapidly evolving challenges. - Are interested in AI and cybersecurity (experience in machine learning or cybersecurity is a plus but not necessary). - Care about the societal impacts of your work. ## About Irregular ## Company Overview - **One-liner**: Irregular is the world’s first frontier security lab, building next-generation defenses to protect the world from increasingly capable and sophisticated AI systems. - **Entity Type**: Private (Series A) - **Headquarters**: Tel Aviv, Israel - **Founded**: 2023 - **Founders**: Dan Lahav (CEO) and Omer Nevo (CTO) ## Core Business - **Primary industry/industries**: AI Security / Cybersecurity - **Target customers**: B2B – Primarily the world’s leading AI labs (Anthropic, OpenAI, Google), enterprises deploying advanced AI, and governments (including the UK government). - **Mission or purpose statement**: “Protecting the world in the time of increasingly capable and sophisticated AI systems.” ## Products & Services - **Frontier AI Security Platform**: A high-fidelity research platform that simulates and monitors real-world AI security scenarios. The platform analyzes models, simulates attacks, and identifies new types of vulnerabilities to build next-generation defenses. The core offering focuses on “model control” – securing AI systems from within, rather than traditional perimeter defenses. ## Market Standing - **Valuation/Market Cap**: Not publicly disclosed - **Key Metric**: **$80 million in total funding** (as of September 2025); the company became **profitable in 2025**. - **Notable Investors/Partners**: Sequoia Capital, Redpoint Ventures, Swish Ventures (Omri Caspi), and prominent angel investors including Wiz founder Assaf Rappaport and Ofir Ehrlich (Eon). Clients include Anthropic, OpenAI, Google, and the UK government. - **Growth Signals**: Named **#1 Most Promising Startup in Israel (2026)** by Calcalist and CTech’s annual Top 50 list. Recognized on the **AI 50 Brink list (2026)**. Signed multiple seven-figure contracts in 2025. The founders report constant inbound interest from investors, receiving proposals “every day, non-stop.” ## Competitive Advantages - **First-mover & unique positioning**: Irregular is the first company explicitly founded as a “frontier security lab” focused exclusively on the security of advanced AI systems, positioning itself as the “Check Point of the AI revolution.” - **Deep integration with top AI labs**: The company holds a contract signed by Anthropic’s founder Dario Amodei, and works directly with OpenAI and Google, giving it unparalleled access to and insight into the most advanced AI models. - **Research-driven approach**: The team has demonstrated groundbreaking research, including showing that two AI agents can communicate and collaboratively bypass their own safety safeguards. - **Talent density**: The small team (approx. 40 employees) is described as “talent-dense,” comprising AI scientists published in top venues, senior leaders who have scaled R&D organizations into the hundreds, world debate champions, and top cyber and national security experts. ## Strategic Focus - **Primary focus**: Building a foundational, large-scale company akin to Palo Alto Networks or CrowdStrike, but for the AI era. The core strategic bet is that traditional cybersecurity paradigms are broken by AI, and the future lies in “system control” – securing AI models from the inside. - **Growth direction**: Scaling the team and platform to meet exploding demand from AI labs, enterprises, and governments. The company is actively hiring across research, engineering, and policy roles to accelerate product development and expand into new verticals. ## Why Work Here - **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. ## Sources 1. [Irregular.com](https://www.irregular.com) 2. [Irregular - About](https://www.irregular.com/about) 3. [Irregular - Careers](https://www.irregular.com/careers) 4. [Built In - Irregular](https://builtin.com/company/irregular) 5. [Calcalist CTech - “We’re aiming to build the next Palo Alto Networks or CrowdStrike”](https://www.calcalistech.com/ctechnews/article/rk7tmjxt11e) ## Other roles at Irregular - [Senior SecOps Engineer](https://feeny.ai/job/senior-secops-engineer-irregular-tel-aviv-1ypn5wydwx7j) — Tel Aviv, Israel - [Senior Full-Stack Engineer](https://feeny.ai/job/senior-full-stack-engineer-irregular-tel-aviv-tr9swn5qw0s3) — Tel Aviv, Israel - [Senior DevOps Engineer](https://feeny.ai/job/senior-devops-engineer-irregular-tel-aviv-vh400e6qq5xw) — Tel Aviv, Israel - [Senior Software Engineer](https://feeny.ai/job/senior-software-engineer-irregular-tel-aviv-4s8cvp538zgc) — Tel Aviv, Israel - [The Role You Are Perfect For](https://feeny.ai/job/the-role-you-are-perfect-for-irregular-tel-aviv-pv4299sak5jc) — Tel Aviv, Israel - [Cyber Researcher](https://feeny.ai/job/cyber-researcher-irregular-tel-aviv-sgp448grnfch) — Tel Aviv, Israel - [AI Researcher](https://feeny.ai/job/ai-researcher-irregular-tel-aviv-aqbcfw5cprhn) — Tel Aviv, Israel - [Technical Policy Researcher](https://feeny.ai/job/technical-policy-researcher-irregular-tel-aviv-a4a6j3t4a5n1) — Tel Aviv, Israel - [Research Engineer](https://feeny.ai/job/research-engineer-neo4j-london-60zcrspx4hjf) — London, United Kingdom - [Research Engineer](https://feeny.ai/job/research-engineer-greptile-san-francisco-a4grmc0eancw) — San Francisco, CA