> Markdown version of [/jobs/ext/4751857-software-engineer-ai-hacking-agents](https://www.wearedevelopers.com/jobs/ext/4751857-software-engineer-ai-hacking-agents). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Software Engineer | AI Hacking Agents - **Company:** Hadrian - **Location:** Amsterdam, Netherlands - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Software System Penetration Testing, C Sharp (Programming Language), Python (Programming Language), Open Source Technology, Software Architecture, Software Engineering, TypeScript, Large Language Models, Agentic-AI, Kubernetes, PydanticAI Framework, Virtual Agents - **Published:** November 17, 2026 - **Apply:** https://www.adzuna.nl/details/5968391838 ## About the Role Are you curious about what happens when AI meets offensive cybersecurity? Interested in AI engineering and building technology that helps organisations uncover and fix real security vulnerabilities?, * Have 3+ years of software engineering experience, or equivalent experience building production software. * Have strong Python skills, with experience building and maintaining reliable production applications. * Have hands-on experience building applications with LLM APIs and an interest in exploring their potential. * Enjoy working through open-ended problems, bringing structure to ambiguity and taking projects from an initial idea through to delivery. * Take a pragmatic and thoughtful approach to engineering, comfortable starting with an MVP, learning from feedback, and improving solutions while keeping reliability in mind. * Enjoy collaborating with others, sharing knowledge, and communicating technical decisions clearly to colleagues with different backgrounds. * Are curious about AI-assisted development and enjoy exploring how new tools can make your workflows more effective. * Are happy to work at least 50% of the time from our Amsterdam office, spending time collaborating with the team in person. * Share our values and work in accordance with them. Bonus points if you have: * Experience building AI agent harnesses or working with frameworks such as LangGraph, LangChain, or PydanticAI. * Experience with TypeScript, Go, or C#. * Experience with Kubernetes, GCP, or AWS. * An interest in or experience with ethical hacking or offensive security. * Contributed to open-source AI projects or repositories. * Published research or shared practical work at AI conferences. * Experience building AI products at a startup or scale-up, or having founded a company. You don't need a background in offensive security or experience with every technology listed above. If you meet the essential requirements and the work sounds interesting to you, we'd love to hear from you! ## Description As a Software Engineer on Hadrian's AI team, you'll help build and improve the AI agents behind our pentesting product, Nova, while developing new AI-powered capabilities that help organisations better understand and address their security vulnerabilities. You'll work across everything from agent harnesses and LLM APIs to prompts, software architecture, and data models, getting involved in the full development journey. We're looking for someone who enjoys exploring complex problems, finding practical solutions, and taking ownership of projects from initial ideas through development, release, and maintenance. And the work doesn't stop once something ships! You'll get to see how your work performs in real-world pentests, investigate challenges as they arise, and use what you learn to continuously improve our agents. Along the way, you'll collaborate closely with other engineers and teams, sharing ideas, learning from one another, and finding thoughtful ways to move forward. If you're excited about combining software engineering and AI to solve meaningful cybersecurity challenges, we'd love to hear from you! * Build and improve AI agents that help uncover security vulnerabilities during authorised penetration tests. * Own projects end-to-end, from understanding a problem and exploring solutions to developing, releasing, and improving them in production. * Evaluate agent performance, using real-world pentest results and feedback to understand what works and where improvements can be made. * Develop reliable, maintainable, and debuggable software across LLM applications, agent harnesses, APIs, prompts, and data models. * Investigate and resolve production issues, helping our AI systems become more reliable and effective over time. * Find practical ways to deliver improvements, balancing thoughtful engineering decisions with the ability to release, learn, and iterate. * Collaborate with colleagues across Engineering and other teams, sharing technical insights, discussing priorities, and working together to solve complex challenges.