AI Engineer (Offensive Security)
CovertSwarm · Engineering · 19d ago
Open to candidates across EU.
Applies on the original listing · via Himalayas
Who can apply
Read straight from the listing, so you know before you spend time on it.
Open to candidates across EU.
“This is a remote role open to candidates based in EU.”
Remote role open to candidates based in the EU.
- Async-first
- The listing doesn't promise async-first working.
- Contractor / B2B
- No mention of hiring international contractors or invoicing.
- Global stipend
- No home office or equipment budget mentioned.
- Annual retreat
- The team gathers in person roughly once per quarter for offsites to align and kick off workstreams.
Read from the listing automatically. Always confirm the details with the company before you accept an offer.
About the role
In this role, you will work alongside offensive security consultants to translate their judgment into reliable, observable, and eval-backed AI systems. You will build end-to-end autonomous hacking agents, benchmark their capabilities using realistic target labs, and deliver internal tooling across Python, TypeScript, LangGraph, Docker, and AWS.
What you'll do
- Design and build architectures for autonomous hacking agents that carry out multi-step offensive workflows end to end.
- Develop backend services, APIs, and interfaces that surface agent capabilities and Gen-AI features to security consultants.
- Build realistic target labs and evaluation harnesses to measure agent performance and validate exploit reliability.
- Conduct applied AI research to evaluate novel techniques and incorporate practical tooling into security delivery.
What you bring
- Strong production engineering experience building, testing, deploying, and debugging reliable applications.
- Hands-on experience developing and evaluating agentic workflows or LLM systems involving tool use, multi-step reasoning, and orchestration.
- Deep understanding of agent failure modes, evaluation metrics, and techniques to turn demos into reliable production systems.
- Strong ownership, judgment, and communication skills to document architecture decisions and explain AI concepts.
About CovertSwarm
CovertSwarm is an offensive security provider dedicated to redefining ethical hacking through continuous testing and cutting-edge engineering.
View CovertSwarm profile & open roles →