{"schemaVersion":"jobsearcher.job.v1","id":"97ebceb7c8c4a8d8335f94c7","url":"https://jobsearcher.com/jobs/97ebceb7c8c4a8d8335f94c7","canonicalUrl":"https://jobsearcher.com/jobs/97ebceb7c8c4a8d8335f94c7","title":"Offensive Security Agent Engineer","description":"We are seeking an Offensive Security Agent Engineer to build the systems that power autonomous offensive security across Apex and the Pensar platform. You'll work at the intersection of software engineering, offensive security, and AI agents, building the harnesses, tools, execution environments, and workflows that allow autonomous agents to discover and exploit vulnerabilities in real-world applications.\nThis is an engineering role focused heavily on web security and agentic systems. You'll work on everything surrounding the model itself: how agents interact with browsers, terminals, proxies, scanners, and custom security tools; how they maintain context and reason across long-running engagements; how they explore complex applications; and how we evaluate whether they are actually becoming better offensive security operators.\nYou'll work closely with our security researchers, AI engineers, and product engineers to turn offensive security techniques into reliable autonomous capabilities. When an agent fails to find a vulnerability, gets stuck in an application, uses a tool incorrectly, or takes an inefficient attack path, you'll dig into why and build the systems that make it better.\nThe ideal candidate is a strong software engineer who understands how modern web applications break, is deeply interested in agentic systems, and wants to build autonomous security infrastructure rather than simply use existing AI tooling.\nKey Responsibilities\nAgent Harness & Infrastructure\n\nDesign and build the agent harness powering autonomous offensive security workflows across Apex and the Pensar platform\nBuild systems that allow agents to reliably interact with browsers, terminals, HTTP proxies, scanners, APIs, filesystems, and other security tooling\nDevelop orchestration for long-running, multi-step offensive security tasks involving reconnaissance, exploitation, validation, and reporting\nBuild abstractions that allow agents to safely and effectively execute tools, inspect results, maintain state, and adapt their approach\nImprove agent context management, memory, task decomposition, planning, and execution across complex engagements\nDesign reliable execution environments for autonomous security agents operating against customer applications and infrastructure\nDebug agent trajectories to understand why an agent succeeded, failed, hallucinated, became stuck, or missed an attack path\nBuild observability and debugging infrastructure for understanding agent behavior at scale\n\nWeb & Application Security\n\nBuild autonomous capabilities for discovering and exploiting vulnerabilities in modern web applications and APIs\nDevelop tooling and workflows around authentication, authorization, session management, API discovery, application state, and complex multi-step attack paths\nEnable agents to navigate and understand JavaScript-heavy applications, authenticated applications, APIs, and modern application architectures\nIntegrate offensive security tooling into autonomous workflows, including proxies, scanners, browsers, custom scripts, and exploitation frameworks\nImplement techniques for identifying vulnerability classes such as access control issues, injection vulnerabilities, SSRF, authentication flaws, business logic vulnerabilities, and other application security weaknesses\nTranslate manual offensive security techniques into primitives and workflows that autonomous agents can execute reliably\nTrack emerging web exploitation techniques and determine how they can be incorporated into Apex\n\nAgent Evaluation & Improvement\n\nBuild evaluation systems for measuring offensive security agent performance against realistic targets\nDevelop benchmarks, test environments, and regression suites that measure whether changes actually improve agent capabilities\nAnalyze agent trajectories and failure modes across real engagementsIdentify systemic weaknesses in agent reasoning, tooling, navigation, and exploitation behavior\nDesign experiments around prompts, models, tools, context strategies, and orchestration approaches\nWork with security researchers to turn newly discovered techniques into reproducible evaluations and agent capabilities\nHelp establish metrics for autonomous pentesting performance beyond simple vulnerability detection\n\nApex & Platform Engineering\n\nContribute directly to Apex, our open source autonomous offensive security tool\nBuild reusable offensive security primitives that can be shared across Apex and the Pensar platform\nDesign APIs and internal interfaces for agent execution, tools, environments, and security workflows\nWork across the stack when necessary to ship new autonomous capabilities into production\nImprove the reliability, performance, and scalability of systems running autonomous security engagements\nCollaborate with platform engineers on infrastructure for securely executing large numbers of concurrent agent workloads\nHelp define the technical architecture of Pensar's autonomous offensive security systems as the platform scales\n\nOffensive Security Research\n\nWork closely with offensive security researchers to understand how experienced human operators approach difficult targets\nConvert researcher techniques, workflows, and intuition into software and agent capabilities\nBuild experimental tooling to test new approaches to autonomous exploitation\nInvestigate difficult targets where existing agents fail and determine what capabilities are missing\nExplore new approaches to browser automation, application understanding, vulnerability discovery, and autonomous exploitation\nContribute to technical research and open source releases around autonomous offensive security\n\nReports To\nCTO\nWe are an equal opportunity employer committed to diversity and inclusion. We welcome applications from all qualified candidates regardless of race, gender, age, religion, sexual orientation, or disability status.\n\n4+ years of professional software engineering, security engineering, offensive security engineering, or equivalent experience\nStrong software engineering fundamentals and experience building production systems\nStrong programming skills in Python, Go, JavaScript/TypeScript, Rust, C/C++, or similar languages\nDeep understanding of modern web applications, HTTP, browsers, APIs, authentication, sessions, and application architecture\nWorking knowledge of common web vulnerability classes and offensive security techniques\nExperience building or working with agentic systems, LLM applications, autonomous agents, or complex tool-using AI systems\nExperience with browser automation technologies such as Playwright, Puppeteer, Chrome DevTools Protocol, or similar tooling\nAbility to debug complex systems across application code, infrastructure, networking, and agent behavior\nComfortable working with Linux, containers, cloud infrastructure, and isolated execution environments\nAbility to independently investigate ambiguous technical problems and turn findings into production systems\nStrong product instincts and an interest in making autonomous systems reliable in messy real-world environments\nBachelor's degree in Computer Science, Cybersecurity, or related field, or equivalent experience\n\nComprehensive health, dental, and vision insurance\nDirect ownership of core autonomous offensive security infrastructure\nOpportunity to build agentic security systems operating against real-world applications\nWork directly with offensive security researchers and engineers pushing the capabilities of autonomous pentesting\nProfessional development budget for conferences, training, and certifications\nSupport for publishing research, open source work, and presenting at industry conferences\nDirect, visible impact on Apex and the Pensar platform\n\n#J-18808-Ljbffr","company":"Pensarai","rawCompany":"pensarai","city":"Eastern","state":"KY","isRemote":false,"isActive":false,"createdAt":"2026-10-03T03:58:13.782Z","occupations":[{"code":"15-1299.05","title":"Information Security Engineers","slug":"information-security-engineers"},{"code":"15-1299.04","title":"Penetration Testers","slug":"penetration-testers"},{"code":"15-1212.00","title":"Information Security Analysts","slug":"information-security-analysts"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Offensive Security Agent Engineer","description":"We are seeking an Offensive Security Agent Engineer to build the systems that power autonomous offensive security across Apex and the Pensar platform. You'll work at the intersection of software engineering, offensive security, and AI agents, building the harnesses, tools, execution environments, and workflows that allow autonomous agents to discover and exploit vulnerabilities in real-world applications.\nThis is an engineering role focused heavily on web security and agentic systems. You'll work on everything surrounding the model itself: how agents interact with browsers, terminals, proxies, scanners, and custom security tools; how they maintain context and reason across long-running engagements; how they explore complex applications; and how we evaluate whether they are actually becoming better offensive security operators.\nYou'll work closely with our security researchers, AI engineers, and product engineers to turn offensive security techniques into reliable autonomous capabilities. When an agent fails to find a vulnerability, gets stuck in an application, uses a tool incorrectly, or takes an inefficient attack path, you'll dig into why and build the systems that make it better.\nThe ideal candidate is a strong software engineer who understands how modern web applications break, is deeply interested in agentic systems, and wants to build autonomous security infrastructure rather than simply use existing AI tooling.\nKey Responsibilities\nAgent Harness & Infrastructure\n\nDesign and build the agent harness powering autonomous offensive security workflows across Apex and the Pensar platform\nBuild systems that allow agents to reliably interact with browsers, terminals, HTTP proxies, scanners, APIs, filesystems, and other security tooling\nDevelop orchestration for long-running, multi-step offensive security tasks involving reconnaissance, exploitation, validation, and reporting\nBuild abstractions that allow agents to safely and effectively execute tools, inspect results, maintain state, and adapt their approach\nImprove agent context management, memory, task decomposition, planning, and execution across complex engagements\nDesign reliable execution environments for autonomous security agents operating against customer applications and infrastructure\nDebug agent trajectories to understand why an agent succeeded, failed, hallucinated, became stuck, or missed an attack path\nBuild observability and debugging infrastructure for understanding agent behavior at scale\n\nWeb & Application Security\n\nBuild autonomous capabilities for discovering and exploiting vulnerabilities in modern web applications and APIs\nDevelop tooling and workflows around authentication, authorization, session management, API discovery, application state, and complex multi-step attack paths\nEnable agents to navigate and understand JavaScript-heavy applications, authenticated applications, APIs, and modern application architectures\nIntegrate offensive security tooling into autonomous workflows, including proxies, scanners, browsers, custom scripts, and exploitation frameworks\nImplement techniques for identifying vulnerability classes such as access control issues, injection vulnerabilities, SSRF, authentication flaws, business logic vulnerabilities, and other application security weaknesses\nTranslate manual offensive security techniques into primitives and workflows that autonomous agents can execute reliably\nTrack emerging web exploitation techniques and determine how they can be incorporated into Apex\n\nAgent Evaluation & Improvement\n\nBuild evaluation systems for measuring offensive security agent performance against realistic targets\nDevelop benchmarks, test environments, and regression suites that measure whether changes actually improve agent capabilities\nAnalyze agent trajectories and failure modes across real engagementsIdentify systemic weaknesses in agent reasoning, tooling, navigation, and exploitation behavior\nDesign experiments around prompts, models, tools, context strategies, and orchestration approaches\nWork with security researchers to turn newly discovered techniques into reproducible evaluations and agent capabilities\nHelp establish metrics for autonomous pentesting performance beyond simple vulnerability detection\n\nApex & Platform Engineering\n\nContribute directly to Apex, our open source autonomous offensive security tool\nBuild reusable offensive security primitives that can be shared across Apex and the Pensar platform\nDesign APIs and internal interfaces for agent execution, tools, environments, and security workflows\nWork across the stack when necessary to ship new autonomous capabilities into production\nImprove the reliability, performance, and scalability of systems running autonomous security engagements\nCollaborate with platform engineers on infrastructure for securely executing large numbers of concurrent agent workloads\nHelp define the technical architecture of Pensar's autonomous offensive security systems as the platform scales\n\nOffensive Security Research\n\nWork closely with offensive security researchers to understand how experienced human operators approach difficult targets\nConvert researcher techniques, workflows, and intuition into software and agent capabilities\nBuild experimental tooling to test new approaches to autonomous exploitation\nInvestigate difficult targets where existing agents fail and determine what capabilities are missing\nExplore new approaches to browser automation, application understanding, vulnerability discovery, and autonomous exploitation\nContribute to technical research and open source releases around autonomous offensive security\n\nReports To\nCTO\nWe are an equal opportunity employer committed to diversity and inclusion. We welcome applications from all qualified candidates regardless of race, gender, age, religion, sexual orientation, or disability status.\n\n4+ years of professional software engineering, security engineering, offensive security engineering, or equivalent experience\nStrong software engineering fundamentals and experience building production systems\nStrong programming skills in Python, Go, JavaScript/TypeScript, Rust, C/C++, or similar languages\nDeep understanding of modern web applications, HTTP, browsers, APIs, authentication, sessions, and application architecture\nWorking knowledge of common web vulnerability classes and offensive security techniques\nExperience building or working with agentic systems, LLM applications, autonomous agents, or complex tool-using AI systems\nExperience with browser automation technologies such as Playwright, Puppeteer, Chrome DevTools Protocol, or similar tooling\nAbility to debug complex systems across application code, infrastructure, networking, and agent behavior\nComfortable working with Linux, containers, cloud infrastructure, and isolated execution environments\nAbility to independently investigate ambiguous technical problems and turn findings into production systems\nStrong product instincts and an interest in making autonomous systems reliable in messy real-world environments\nBachelor's degree in Computer Science, Cybersecurity, or related field, or equivalent experience\n\nComprehensive health, dental, and vision insurance\nDirect ownership of core autonomous offensive security infrastructure\nOpportunity to build agentic security systems operating against real-world applications\nWork directly with offensive security researchers and engineers pushing the capabilities of autonomous pentesting\nProfessional development budget for conferences, training, and certifications\nSupport for publishing research, open source work, and presenting at industry conferences\nDirect, visible impact on Apex and the Pensar platform\n\n#J-18808-Ljbffr","datePosted":"2026-10-03T03:58:13.782Z","dateModified":"2026-10-03T03:58:13.782Z","hiringOrganization":{"@type":"Organization","name":"Pensarai","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Eastern","addressRegion":"KY","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"97ebceb7c8c4a8d8335f94c7"},"url":"https://jobsearcher.com/jobs/97ebceb7c8c4a8d8335f94c7"}}