As AI Software Engineer, you will help build autonomous AI agents to plan, reason, and operate security tooling for controlled environments. You will work on a remote UK-based team within a leading cybersecurity technology company, shaping how penetration testing is automated. You will design and deploy AI agents, sandboxed labs, and scalable production systems, with guardrails and monitoring. You will collaborate with security researchers to translate offensive techniques into agent behavior and drive performance through prompt engineering and tool orchestration. This role offers the chance to impact real-world security while working across a polyglot stack in a fast-paced environment.
Pay / Benefits
remote work
competitive salary
Responsibilities
Design, build and deploy AI agents to automate penetration testing
Develop sandboxed cyber-lab and range infrastructure with containers and Kubernetes
Deliver AI features from design to production with guardrails and monitoring
Improve agent performance via prompt engineering, tool orchestration, evaluation and cost optimisation
Integrate security tools and ensure safe operation within defined scopes
Collaborate with security researchers to translate offensive security techniques into agent behavior
Lead code reviews and technical design sessions while supporting other engineers
Contribute to reliable, scalable production systems across a polyglot technology environment
Key requirements
Significant software engineering experience with proven ability to scale production systems
Strong Python development skills and willingness to learn Go
Hands-on experience building/operating production AI apps using LLMs and agentic frameworks
Understanding of RAG, MCP, LangGraph or similar technologies including tool integration and prompt design
Experience creating reliable AI agents through evaluation, guardrails and cost optimisation
Proficiency with Docker, Kubernetes and isolated sandbox environments, with cloud experience; GCP advantageous
Knowledge of microservices, gRPC, API design, asynchronous messaging and platforms such as Pub/Sub or Kafka
Strong testing, communication and collaboration skills, and interest in how systems are compromised
We use essential cookies to make this site work. With your permission we would also like to use the optional cookies below. Nothing optional is set until you choose, and you can change your mind at any time from "Cookie settings" at the bottom of every page. Cookie policy.
Essential — keep the site working and secure, and remember the choice you make here. Always on.