Penetration Tester

I’m hiring an Offensive Security Researcher to join a stealth startup that's building a platform where AI doesn’t just assist with security – it attacks. The company is backed by Cyberstarts and other top-tier investors, and led by a group of highly experienced professionals in cybersecurity, engineering, and research.

They’re developing autonomous red teaming agents that simulate real-world adversaries, from reconnaissance to lateral movement – and this role is all about shaping how those agents think and act.

What you’ll do?

• Translate attacker tradecraft into decision trees, playbooks, and attack workflows
• Guide AI researchers and engineers on how attackers really operate
• Build threat models and test scenarios for autonomous attack simulation
• Conduct hands-on research to validate real-world attack paths
• Help define how AI “decides” what to attack, when, and how

What you bring?

• 4+ years in offensive security, red teaming, or adversary simulation
• Background in consulting – with proven experience in complex attack campaigns
• Expertise in MITRE ATT&CK and offensive methodologies
• Practical experience across AD, cloud environments, and web applications
• Ability to work closely with engineering teams and abstract complex attacker behavior into
• logic-based systems

Why it’s different here?

You won’t be running traditional pentests. You’ll be designing how AI red teamers operate – from tactics to decision-making. If you’ve ever wanted to encode your offensive intuition into a system that actually learns from it – this is that opportunity.

Tech stack

Python, offensive security tooling, autonomous agents, MITRE ATT&CK, Active Directory, cloud environments, security automation, AI logic integration