Description
We are seeking an Applied AI Engineer to build the customer-facing cyber service and use-cases on top of our cyber harnesses. You will turn 'we have agents' into 'we shipped something a client uses.' This role is about composing red-team/blue-team agentic workflows, configuring harnesses for real-world scenarios, and delivering value directly to clients.
Your work will bridge the gap between our foundational cyber harnesses and the agentic solutions that clients deploy. While SWE-Cyber makes the platform robust and scalable, and Pentesters run the solution and guide the direction, you will focus on building the agentic use-cases and client-facing service that solve real security problems.
Client-Facing Agentic Solutions
- Compose red-team / blue-team agentic workflows for production use-cases
- Configure harnesses for cloud defense, vulnerability scanning, dynamic red-teaming, and penetration testing scenarios
- Work directly on client use-cases, translating security requirements into agentic solutions
- Turn prototype agents into deployed services that clients rely on
Context Engineering & Orchestration
- Design and implement context engineering that enables agents to operate effectively in cybersecurity domains
- Orchestrate multi-agent systems for complex security workflows
- Build the agentic layer that sits between the harness and the client
Service Delivery
- Ship fast and iterate based on client feedback and real-world performance
- Operate independently while leveraging internal building blocks and frameworks
- Collaborate with pentesters to ensure domain accuracy and effectiveness
- Partner with SWE-Cyber to ensure the platform supports your use-case requirements
About you
- Strong applied AI engineer with hands-on experience building agents, LLM orchestration, context engineering, evals, and RAG systems
- You ship fast, with a bias toward action and delivery
- Operate independently with a customer-led mindset
- Able to reuse internal components and bricks effectively
- Some cyber context is a real plus, but not mandatory - we can pair you with pentesters for domain depth
- Strong problem-solving abilities and attention to detail
- Excellent communication skills and collaborative attitude
It would be ideal if you also have:
- Genuine cyber or pentest knowledge
- Experience building agentic harnesses or multi-agent systems end-to-end
- Strong background in evals and benchmarking of agent systems
- Experience with security tooling or workflows
- Prior work on production AI systems in regulated or high-stakes environments