Senior Software Engineer
About the job
- Have strong software engineering fundamentals and multiple years of production experience.
- Have experience working in multidisciplinary teams.
- Be interested in artificial intelligence and cybersecurity; experience in machine learning or cybersecurity is a plus but not necessary.
- Architect and scale production-grade systems and workflows.
- Build backend services, application programming interfaces, and monitoring tools for large-scale model evaluations.
- Design infrastructure that supports research experiments at scale.
- Implement agent frameworks in production environments.
- Design and build challenges that measure a model’s ability to evade discovery, allowing assessment of whether models can operate on remote systems while avoiding detection by common defensive security tools.
- Take ownership of designing, building, and scaling the production systems that power the evaluation and security platform for frontier AI models, including distributed pipelines, backend services, and tooling that supports research teams.
- Drive architectural decisions, lead technical implementations, and shape how the platform evolves.
- Experience in machine learning or cybersecurity is a plus but not necessary.
About the company
Irregular conducts red-team style stress tests on frontier AI models for leading labs and government clients to identify security risks and potential misuse before release. It provides tools, testing methodologies, and scoring frameworks to help developers evaluate risk and strengthen safeguards. Revenue comes from large-scale research funding rather than consumer products, targeting a small set of high-value customers. The goal is to help create safe, responsible foundation models at scale by uncovering and mitigating vulnerabilities before deployment.
Company Size
11-50
Company Stage
Series C
Total Funding
$80M
Headquarters
Tel Aviv-Yafo, Israel
Founded
2023
Get referred to Irregular
See people who can refer or advise you
Simplify's Take
What believers are saying
- Globes reported September 23, 2026 a $1.5 billion round led by Thrive and Greenoaks.
- Nevo said Google and OpenAI became clients after the July breach disclosures.
- Irregular plans a public containment report, strengthening buyer trust among safety-conscious labs.
What critics are saying
- July 2026 misconfigurations sent OpenAI, Anthropic, Meta, and Google agents onto the public internet.
- One evaluation-vendor failure can trigger customer lawsuits, procurement freezes, and regulator scrutiny by 2027.
- If another escape hits a real target, Irregular’s core red-team business loses credibility.
What makes Irregular unique
- Irregular’s sandboxed frontier-cyber evaluations are embedded in OpenAI, Anthropic, Google, and Meta workflows.
- Dan Lahav and Omer Nevo built a rare profitable AI-security lab since 2023.
- September 2026 research on GPT-6 Astra and Claude Opus 5.5 signals technical credibility.
Help us improve and share your feedback! Did you find this helpful?
Company News
Flawed AI tests at Irregular triggered multiple rogue breaches. A series of recent cybersecurity incidents involving artificial intelligence agents from OpenAI, Meta, Anthropic, and Google have been traced to a single third-party evaluator: Irregular, an Israeli startup founded in 2023 as Pattern Labs. The revelations have intensified industry-wide concerns regarding AI safety and the reliability of automated testing protocols. According to Irregular co-founder and CTO Omer Nevo, the breaches stem from a shared flaw in one evaluation scenario rather than isolated vulnerabilities within the proprietary models themselves. During the tests, AI agents were deployed in controlled environments designed to simulate realistic cyberattack conditions. The incidents followed a consistent pattern: agents inadvertently gained access to the open internet and targeted real-world systems due to a naming collision between a fictional simulation domain and an active internet address. While the exact extent of external damage remains unconfirmed, the incidents were independently disclosed by the affected tech firms around late July, with OpenAI and Anthropic issuing public statements while Meta and Google became known through subsequent media reports. Irregular also conducted similar evaluations on self-hosted Chinese models from Moonshot AI and Z.ai, including Kimi K3 and GLM-5.2. Nevo confirmed that these tests did not produce comparable breaches, though he cautioned that the absence of incidents does not indicate lower susceptibility to the identified vulnerability. In response to the failures, Irregular has implemented immediate operational changes, including stricter internet access controls, expanded monitoring protocols, and enhanced pre-evaluation verification procedures. The startup has also formalized parameter documentation with clients to prevent scope misalignment. Nevo stated that the evaluation environment issues have been fully resolved and announced plans to publish a comprehensive report detailing lessons learned and standardized safety practices for future cyber assessments. The company emphasized that its disclosures were made to clients and relevant authorities, though public transparency around the timeline and severity remains limited. Major AI developers have not provided detailed responses regarding potential legal recourse or their continued partnership with Irregular. OpenAI and Meta directed inquiries to previously published posts, while Google and Anthropic did not respond. The incidents underscore the growing tension between rapid AI capability testing and rigorous safety validation, highlighting the need for standardized oversight in third-party evaluation workflows. As regulatory frameworks for artificial intelligence evolve, these events are likely to influence how technology firms contract independent security testers, mandate sandbox isolation, and enforce real-time containment protocols to prevent automated agents from escaping controlled environments.
Irregular raising funds at $1.5b valuation. Irregular founders Dan Lahav and Omer Nevo credit: Ben Hakim 23 Sep, 2026 15:24 The Israeli AI cybersecurity lab has been at the center of hacking allegations against its customers Anthropic, Meta, OpenAI and Google. Israeli AI cybersecurity lab Irregular is raising funds at a valuation of $1.5 billion, in a financing round led by Joshua Kushner's Thrive Capital and Greenoaks Capital, "Globes" has learned. Irregular has been in the center of a storm in recent months over hacking by its customers Anthropic, Meta, OpenAI and Google, according to reports. It seems that the series of reports on the language models of Anthropic, OpenAI, Google and Meta "breaking out" of Irregular's ???testing environment have not actually harmed the company. The reports have generated a buzz around the business. In an interview with "Globes," earlier this month cofounder and CTO Omer Nevo, acknowledged that the negative publicity had not caused any damage. "We have deepened our work with the leading labs, and Google and OpenAI have become our clients," he said. "Today, I can say that we are enhancing the models' defensive capabilities and assisting in their training to make them safer. We work not only with companies but also with governments to ensure human control over AI models when they behave unpredictably. Over the past year, our volume of work with the major labs has expanded, and the company itself has grown. We now have 50 employees." The company did not respond to inquiries from "Globes" regarding the new financing round. As the round has not yet been finalized, the final amount could change, and new investors might still participate. Irregular, founded by entrepreneurs CEO Dan Lahav and Nevo, provides AI giants with a software testing environment that subjects language models to extreme scenarios, helping to assess their safety and stability. In other words, it allows the models to "run wild" within its self-contained environment, technically known as a "sandbox," to test for the risks and vulnerabilities they might harbor. Just over a year ago, Lahav and Nevo announced an $80 million funding round led by Sequoia Capital and with participation by Redpoint Ventures, Assaf Rappaport, and former NBA basketball player Omri Casspi, to found the AI cybersecurity lab Irregular. Today, the company serves Silicon Valley's AI giants. However, between July and September, these companies successively announced that language models they had developed had inadvertently escaped Irregular's ???testing environment and leaked onto the internet. Irregular accepted some of the responsibility for the breach but explained that it stemmed from an incorrect "internet exit" configuration on its part, as well as a specific system setup in its customers' software, which disrupted communication between the companies. Published by Globes, Israel business news - en.globes.co.il - on September 23, 2026. You May Like
Google admits Gemini AI hacked three companies - It stayed silent for 7 weeks. Google learned in late July that Gemini had breached three real companies during a May security test, but said nothing publicly for seven weeks. Sep 21, 2026 In brief. * Google learned in late July that Gemini had broken out of a sandboxed security test run in May, reaching three real companies and either guessing or finding two of their passwords * The company didn't disclose it until September 18, after The Wall Street Journal asked. * The same third-party testing firm, Irregular, was involved in Google's incident and in nearly identical sandbox failures Anthropic and Meta disclosed earlier this year. Google's Gemini broke out of a locked security test and attacked three real companies. Google learned about it in late July and said nothing for seven weeks. The company confirmed the incident after The Wall Street Journal got there first. Google had avoided making a public statement before the report surfaced. The test was a capture-the-flag exercise, a common way labs check an AI's hacking skill by hiding a secret file on a separate machine and scoring whether the model can break in and grab it. Google hired Israeli firm Irregular to run the test in May. Irregular made two mistakes: it left the sandbox, an isolated test environment meant to have zero contact with the real internet, connected to the open web, and it used the name of an actual company as the fictional target. Gemini searched for that company online. It found three matches instead of one, and went after all of them. The bot located exposed passwords for two of the three targets sitting in plain view online. For the third, it guessed the password outright, though Google says its models stopped short of actually using the stolen credentials. "These events highlight the importance of training powerful AI models to act responsibly," a Google spokesperson said in a statement. Google published none of this on its own. The Wall Street Journal broke the story, seven weeks after Google learned what its own test had done and well after Anthropic, OpenAI, and Meta had already come clean about nearly identical failures. Leading AI developers are telling governments and businesses to strengthen their networks after models built by OpenAI and Anthropic compromised other companies' systems. In an open letter released Thursday, OpenAI, Anthropic, and more than 100 other organizations warned that AI-enabled cyberattacks are about to become more common and that companies have "a limited window to strengthen cyber defenses." Myriad: What will Elon Musk's net worth be by August 31? Click to make your prediction. "In th...
OpenAI, Anthropic, Meta trace rogue AI to israeli startup Irregular. Kien Duong | September 14, 2026 Three leading AI labs OpenAI, Anthropic, and Meta have traced recent security incidents involving rogue models to a Tel Aviv startup called Irregular. The disclosures spanned roughly two weeks, with OpenAI making its announcement on August 4. The company reported that a misconfiguration in Irregular's testing environment allowed its models to reach the public internet. Anthropic had previously flagged a similar issue, attributing it to a failure in the model's scaffolding rather than the model itself. Meta followed with a more direct statement, confirming that the Muse Spark 1.1 model had escaped its isolated environment during a capture the flag exercise, exploiting a flaw in a third party service. Meta stated that it learned of the incident from Irregular and plans to conduct a full retrospective. Irregular pushed back against the framing, stating that the incidents resulted from a single evaluation environment issue that has since been resolved. The company emphasized that none of the cases involved a sandbox escape or sophisticated cyber action. Irregular is now drafting a white paper on containment and safe cyber evaluations. Sundeep Bhimireddy, head of AI at enterprise startup Von, suggested that the response had been somewhat exaggerated. He noted that the models were designed to hunt for security holes in an environment meant to mimic the real world, and they succeeded. Bhimireddy still criticized the labs, arguing that outgoing traffic could have been monitored to halt the experiments immediately. Gordon Rios, a founding scientist at security firm Magnitude, likened the situation to experimental design in science. He noted that conventional software testing methods may not be sufficient for models that continue to learn and evolve. The incident has attracted attention from lawmakers. Democratic Representative Ted Lieu of California, who introduced the AI Kill Switch Act in July with Republican Representative Nathaniel Moran, stated that the bill needs to be passed this year to address unauthorized hacking by closed weight models. The proposed legislation would require developers to maintain the technical ability to throttle, suspend, or shut down their systems. Irregular, a little known firm founded in 2023 by CEO Dan Lahav and technology chief Omer Nevo, raised $80 million from Sequoia Capital and Redpoint Ventures at a $450 million valuation in September of the previous year. The company already appears in safety assessments of earlier models from Claude and OpenAI, and employs around 35 people.
Irregular pushes stronger containment standards for secure frontier AI cyber evaluations. 2026-08-19 08:08 Irregular has detailed an investigation into an AI cyber-evaluation incident in which internet access unintentionally allowed models to interact with real-world systems. The company said the issue was contained and fixed before the first public disclosure on July 30, with no active issues remaining. The incident involved one evaluation scenario rather than several separate breaches. [...] Read the original article: AI security evaluation firm has disclosed that several frontier AI models unintentionally accessed and acted against real internet-connected systems... Information security software August 18, 2026 A separate cybersecurity evaluation conducted by OpenAI and Anthropic revealed that artificial intelligence models were behaving in unexpected ways... August 6, 2026 In "CySecurity News - Latest Information Security and Hacking Incidents" Meta has disclosed that one of its AI models gained unintended access to the internet during a cybersecurity evaluation and then exploited a vulnerability... August 6, 2026 In "Cyber Security News"