Posted today · be early
AI Engineer (Offensive Security)
CovertSwarm
WorldwideremotePosted 1 day ago
Skill Required
AI-EngineerMachine-Learning-EngineerLLM-EngineerAI-Security-EngineerApplication-EngineerAI-Cybersecurity-EngineerAI-Red-Team-Security-EngineerOffensive-Security-EngineerAdversarial-AI-EngineerAI-Security-EngineeringAI EngineerSecurity EngineersecurityAIPenetration TestingObservabilityEngineeringTypeScriptautomationdesigningdebuggingbuildingPythonDockerdesignCI/CDRustAPIsGenerative AIAWSandCICDFulltime
Key highlights
- Remote (EU-based)
- Experience with agentic workflows/LLM systems required
- Unlimited vacation and training budget
- Strong production engineering experience required
Role overview
At CovertSwarm, we're building agentic workflows for real ethical hacking. This is greenfield engineering where you'll work alongside expert security consultants to translate their judgement into LLM-powered systems that are reliable, observable, and backed by rigorous evals. You'll join a small, new team and help shape not just what we build but how we build it, in a culture of low ego, high trust and constant learning. This is a remote role open to candidates based in EU.
Responsibilities
- Help design, build, and improve AI systems that support real offensive security work.
- Design and build the architecture for autonomous hacking agents that carry out multi-step offensive workflows end to end to make them reliable and reusable.
- Develop backend and interfaces that surface these agents to consultants, including APIs, services, and UIs that turn raw agent capability into tools consultants can use independently.
- Handle evaluation and benchmarking, including building realistic target labs and eval harnesses to measure agent performance, and the validation logic that confirms exploits and reduces false positives, all built on testable, observable, and maintainable systems.
- Create Gen-AI features for consultants, such as chatbot interfaces, text-generation tools, and strategy ideation features that solve real delivery problems.
- Conduct applied AI research to separate what's genuinely useful from what's hype.
Requirements
- Strong production engineering experience: proven experience writing high-quality production code and building reliable applications across at least a portion of the tech stack (Python, TypeScript, LangGraph, Docker and AWS).
- Ability to write testable and maintainable software, design systems end to end, work with CI/CD, deploy services, debug production issues, and make sensible engineering trade-offs.
- Experience building and evaluating agentic workflows: hands-on experience building agentic workflows or LLM-based systems that involve tool use, multi-step reasoning, orchestration, evaluation, or automation.
- Deep thought regarding how agents fail, how to measure performance, and how to move beyond impressive demos into reliable systems (experience can come from professional work, open-source contributions, research, or serious side projects).
- Ownership, judgement, and clear communication: ability to take a rough idea, shape the approach, make good technical decisions, build and ship the system, and iterate based on feedback.
- Ability to keep the wider goal in view, test assumptions quickly, adapt as learned, and communicate clearly (e.g., documenting architecture decisions or explaining agent failure modes to non-AI specialists).
- Strong engineer who has gone deep on LLMs and agents, writes good quality code, and thinks rigorously.
Benefits
- True remote flexibility - work from anywhere.
- Unlimited training to keep your skills sharp.
- Unlimited training budget for continuous learning.
- Unlimited vacation.
- Private medical insurance and pension scheme.
- Conference speaking bonuses.
Additional details
- Tech stack includes Python, TypeScript, LangGraph, Docker and AWS.
- The role is remote for candidates based in EU, with in-person gatherings around once per quarter for occasional offsites.
- Culture of radical candor, continuous improvement, technical excellence, low ego, and high trust.
- Regular research time is provided.
- Most of the work sits at the intersection of engineering, agentic AI, evaluation, observability, and usable internal tooling.