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
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 Technical Policy researcher at Irregular, you'll tackle some of the biggest and most complex questions of AI development and deployment. Your work outlining problems, solutions and principles for governments, frontier labs, and deployers will shape the emerging field of AI security.
Representative projects:
Threat modeling and fleshing out in what specific way could a strong cyber-capable model cause harm.
Taxonomies for dangerous AI capabilities or mitigations.
Policy proposals for models' refusal policy (which prompts models should refuse to follow).
Following up on publications and news on AI policy, AI risks and mitigations, and technical AI research.
Writing academic papers and blog posts detailing our research around evaluation theory or mitigation recommendations.
Publishing your research and/or delivering research to our customers.
You may be a good fit if you have
Strong research skills in both quantitative and qualitative methods.
Strong writing skills, and experience as an academic (or industry equivalent) writer or analyst.
Interest in AI and specifically AI security.
Technical proficiency.
Background in AI/cybersecurity - a big advantage
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 cyber researcher at Irregular, you will be at the forefront of research on AI security. You will engage with questions such as how to protect the weights of an advanced model against cyber threats, and how to evaluate cyber capabilities such as AI’s ability to exploit vulnerabilities, carry out network attacks, and develop malware. This role sits at a unique intersection of cybersecurity expertise and AI capabilities, where your background in vulnerability and security research will help shape the future of AI security.
Representative projects:
Expanding the quantity, quality, and variety of our cyber capabilities evaluation challenges (e.g. constructing original CTF-style vulnerability & exploitation challenges, network attack simulation challenges, and more, including original types of challenges).
Leading research into methods to mitigate cybersecurity risks related to the misuse of AI, the theft of model weights, or risks associated with integrating models with dangerous capabilities in AI agents.
Publishing your research and/or delivering research to our customers.
Advising and supporting the development of the products we’re building.
Representative research questions about AI frontier models:
Can an AI find and exploit 0-days?
What’s the best way to measure a CTF challenge's difficulty level vs. an AI player's skill level?
Can an AI elevate an average computer science student’s cyber capabilities to that of a nation-state?
You may be a good fit if you:
Have a strong background in vulnerability/security research & development such as having found vulnerabilities/CVEs, analyzed malware, researched detection methods for attacks, developed pentesting products or other attack tools, participated in CTF competitions or authored CTF challenges, or participated in other types of security research & development.
Work well in a multidisciplinary team and can adapt to rapidly evolving challenges.
Care about the societal impacts of your work.
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.
We’re always excited to meet people who excel at what they do, care deeply about AI Security, and want to solve problems that are both challenging and important.
If you thrive in ambiguity, bring unique skills or perspectives, and are eager to contribute to our mission, we’d love to hear from you - even if there’s no “perfect” role listed yet.
Tell us what you bring. We’ll explore how to build with you.
","descriptionPlain":"We’re always excited to meet people who excel at what they do, care deeply about AI Security, and want to solve problems that are both challenging and important.\n\nIf you thrive in ambiguity, bring unique skills or perspectives, and are eager to contribute to our mission, we’d love to hear from you - even if there’s no “perfect” role listed yet.\n\nTell us what you bring. We’ll explore how to build with you.\n\n"},{"id":"3258b769-ba83-49fa-ba11-8cb98494dee9","title":"Senior Software Engineer","department":"R&D","team":"Engineering","employmentType":"FullTime","location":"Tel Aviv, Israel","secondaryLocations":[],"publishedAt":"2025-11-26T12:52:47.327+00:00","isListed":true,"isRemote":false,"workplaceType":"OnSite","address":{"postalAddress":{"addressRegion":"Tel Aviv District","addressCountry":"Israel","addressLocality":"Tel Aviv"}},"jobUrl":"https://jobs.ashbyhq.com/Irregular/3258b769-ba83-49fa-ba11-8cb98494dee9","applyUrl":"https://jobs.ashbyhq.com/Irregular/3258b769-ba83-49fa-ba11-8cb98494dee9/application","descriptionHtml":"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 Software Engineer at Irregular, you will take ownership of designing, building, and scaling the production systems that power our evaluation and security platform for frontier AI models.
Your work will focus on creating robust, resilient, and high-performance infrastructure—whether that’s distributed pipelines, backend services, or tooling that supports our research teams.
This role is engineering-first with a strong research and cyber component. You will develop systems that must run reliably in production, integrate with external partners, and support large-scale data, experiments, and automated evaluations. You’ll drive architectural decisions, lead technical implementations, and shape how our platform evolves.
Representative Responsibilities:
Architecting and scaling production-grade systems and workflows.
Building backend services, APIs, and monitoring tools for large-scale model evaluations.
Designing infrastructure that supports research experiments at scale.
Implementing agent frameworks in production environments
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.
You may be a good fit if you:
Have strong software engineering fundamentals and multiple years of production experience.
Have experience working in multidisciplinary teams, and can adapt to rapidly evolving challenges.
Enjoy working at the intersection of engineering and applied research.
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
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 Irregular’s Senior DevOps Engineer, you will play a critical role in shaping our infrastructure, deployment pipelines, and operational foundations. This is a hands-on, high-ownership role with real influence over how the company builds, deploys, and operates its systems in production.
You’ll be building infrastructure that supports work with frontier AI labs such as Google, Anthropic, and OpenAI, and meets the scale, security, and reliability standards this ecosystem requires. This includes architecting ephemeral, on-demand environments, and spinning up and tearing down multi-service deployments (VPCs, compute, serverless components, and more) as needed.
You will work closely with research, engineering, security, and leadership to design and maintain scalable infrastructure, improve system reliability, and enable fast, safe, and secure product delivery.
Key Responsibilities
Own and evolve Irregular’s cloud infrastructure, with a strong focus on scalability, security, and reliability
Design, build, and maintain end-to-end CI/CD pipelines and deployment workflows
Lead and continuously improve containerized environments (Docker, Kubernetes)
Build and maintain Infrastructure as Code and automation frameworks (e.g., Terraform)
Own production readiness: availability, monitoring, logging, alerting, and incident response
Work closely with engineering and research teams to support development, testing, and production needs
Drive improvements in system performance, reliability, and security posture
Take part in - and often lead architectural decisions and long-term infrastructure planning
Act as a key operational owner in a fast-growing startup, setting best practices and standards
Requirements
5+ years of hands-on experience as a DevOps / Infrastructure Engineer in production environments
Strong, hands-on experience with AWS (architecture, networking, security, and cost awareness)
Proven experience with containerization and orchestration (Docker, Kubernetes) in production
Hands-on experience designing and maintaining CI/CD pipelines (e.g., GitHub Actions or similar)
Strong experience with Infrastructure as Code and automation (e.g., Terraform)
Ability to take end-to-end ownership and operate independently in an early-stage, high-ambiguity environment
Nice to Have
Experience working closely with research or security teams in production environments
Background supporting data-heavy, distributed, or high-scale systems
Familiarity with monitoring, observability, and alerting tools (e.g., Prometheus, Grafana, Datadog)
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 Senior FullStack Engineer, you’ll join our engineering team and help build the next generation of Irregular’s products as they evolve into intuitive, polished, and powerful experiences for some of the most sophisticated AI organizations in the world.
This is a highly impactful role for an engineer with strong frontend expertise who cares deeply about product quality and user experience, and can both build scalable systems and help lead the technical direction of the frontend. You’ll work closely with exceptional engineers, researchers, and founders to turn deeply technical capabilities into user-facing products that are clear, elegant, and highly effective.
Representative Responsibilities:
Build and own full-stack product features end-to-end
Help shape the next generation of the company’s products
Lead the technical direction of the frontend architecture, development standards, and engineering culture
Build polished, high-quality user experiences for highly technical users
Collaborate closely with engineers, founders, and product stakeholders on product and technical decisions
Take ownership of projects from idea to production with high autonomy and impact
What we're looking for:
Strong full-stack engineering experience with deep frontend capabilities
Hands-on frontend experience with React/Angular/TypeScript and modern frontend frameworks
Backend development experience with scalable production systems
Ability to work independently and lead projects from idea to production
Strong product intuition and passion for building exceptional user experiences
Comfort working closely with designers and building polished, pixel-perfect UIs across devices and screen sizes
Commitment to code quality, maintainability, and testing as part of the development process
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.
We’re looking for a Senior SecOps Engineer to own and evolve the security infrastructure, tooling, and controls that protect Irregular’s engineering environment.
This is a hands-on security engineering role focused on building, implementing, and operating the systems that enable our engineering teams to work securely at scale. You’ll work closely with our Infrastructure Engineers and the broader Engineering team to embed security into our infrastructure and development environment without slowing teams down.
You’ll take ownership of security tooling and posture management across our environment — from evaluating and deploying new security technologies to continuously improving how we identify, prioritize, and remediate security risks.
We’re looking for someone with a strong background in Security Operations, Infrastructure Security, or Security Engineering who has operated and secured modern engineering environments.
Own, operate, and continuously improve Irregular’s security infrastructure, tooling, and controls across cloud infrastructure, engineering systems, identity, and endpoints.
Evaluate, implement, and integrate security technologies across our engineering environment.
Own security posture and vulnerability management, including identifying, prioritizing, tracking, and driving remediation of security risks.
Partner closely with Infrastructure and Engineering teams to identify security gaps and implement practical, scalable solutions.
Integrate security tooling into engineering workflows, including vulnerability and dependency scanning tools
Build and improve security monitoring, detection, alerting, and incident response capabilities.
Automate security operations and controls to improve coverage, consistency, and efficiency.
Significant hands-on experience in Security Operations, Infrastructure Security, or Security Engineering.
Experience owning security infrastructure and tooling in a modern, cloud-based AWS environment.
Strong understanding of cloud and infrastructure security, identity and access management, endpoint security, vulnerability management, and security monitoring.
Hands-on experience evaluating, deploying, integrating, and operating security tools and security posture management platforms.
Experience implementing security controls in close collaboration with Infrastructure and Engineering teams.
The ability to independently identify security gaps, design solutions, and drive implementation end-to-end.
Strong ownership mentality and the ability to operate effectively in a fast-moving, high-ambiguity environment.
Hands-on experience with,
penetration testing, security research or offensive security.
cloud security posture management (CSPM) and related security platforms.
application Security and secure software development best practices.
building security automation or internal security tooling.
Experience translating offensive security knowledge into detection engineering, incident response, threat hunting, and security monitoring improvements.
Hands-on security training or certifications demonstrating strong practical offensive and defensive security skills, such as OSCP, OSCE, or equivalent.
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.
Our work helps identify emerging threats and develop the defenses needed to deploy increasingly powerful AI safely and securely.
We’re looking for a Senior Talent Acquisition Partner to help build the team tackling some of the most challenging problems in AI security.
This is a hands-on role owning end-to-end recruitment across Engineering, AI Research, Cybersecurity, and Product. You’ll work closely with hiring managers and leadership to understand complex hiring needs, find exceptional people, and guide thoughtful hiring decisions.
You’ll combine proactive sourcing with close candidate relationships and strong execution, while helping shape how we recruit as the company grows.
Own full-cycle recruitment for technical and product roles, from defining the hiring profile through sourcing, interviews, and offers.
Partner closely with hiring managers to understand their teams’ needs, refine role requirements, and build effective interview processes.
Develop targeted sourcing strategies to identify and engage hard-to-reach candidates across engineering, AI, and cybersecurity.
Build relationships with prospective candidates, understand their motivations, and help them explore how their experience and interests connect to our work.
Keep hiring processes moving through clear communication, timely feedback, and close coordination with candidates and interviewers.
Support hiring managers and interviewers in evaluating candidates, aligning feedback, and making well-informed decisions.
Use pipeline data and market insights to identify gaps, adjust search strategies, and improve recruitment processes.
5+ years of technical recruitment experience, including in a fast-growing startup or technology company.
A strong track record of hiring for complex technical roles and a good understanding of engineering, cybersecurity, or AI talent.
Strong hands-on sourcing skills, including talent mapping, targeted outreach, and creative approaches to reaching passive candidates.
Experience partnering with hiring managers, asking thoughtful questions, and challenging assumptions when needed.
The ability to build trust with candidates and communicate technical opportunities clearly and credibly.
Strong ownership and organization, with the ability to manage multiple searches and drive processes independently in a fast-moving environment.
Sound judgment and the ability to balance hiring urgency with a high bar for talent and candidate experience.
Excellent written and spoken English.
Experience working at cyber-security company- Advantage
Experience in global recruitment- nice to have