About
Most vulnerability scanners flag everything and let humans sort it out. The challenge is building agents that can reason over scanner output with real environment context — and actually act on what matters. That's the problem this backend exists to solve.
This is a Series A AI cybersecurity startup applying LLMs and agents to vulnerability management, with an engineering team of ~15 fully remote across European time zones.
The stack is Python, FastAPI, Postgres, Kubernetes, and AWS. This role is about deploying agents into production reliably — not model training or research.
What you'll do
- Design and build backend systems that support complex agentic workloads end-to-end
- Develop and scale AI agents that triage, prioritise, and remediate security vulnerabilities
- Integrate LLMs and AI services into production applications, including orchestration and tool use
- Own the full development lifecycle: architecture, deployment, maintenance, and iteration
- Monitor and improve application performance, security, and scalability
- Define coding standards and best practices as the team grows
- Mentor engineers and contribute to technical direction as the organisation scales
What you'll need
- 7+ years of backend engineering experience with strong Python fundamentals
- Solid RESTful API design, database management, and server-side framework experience
- Hands-on experience integrating LLMs or agent-style AI services into production systems
- Familiarity with agent frameworks such as LangChain, LlamaIndex, or similar
- Cloud experience, ideally AWS, with DevOps practices including CI/CD and containerisation
- Comfort operating in a fast-moving environment where requirements evolve quickly
Shortlisted candidates will be contacted within 48 hours.
