Penetration Tester

Penetration Tester / Red Teamer

About the Company

The company is developing autonomous offensive-security agents designed to identify vulnerabilities and demonstrate how they can be exploited. Its mission is to bring together security research and engineering to transform how organisations test and secure their systems.

The team combines practical offensive-security expertise with the development of AI-powered tools that can discover, validate and reproduce security vulnerabilities.

About the Role

The company is looking for a hands-on Penetration Tester / Red Teamer to conduct and support security testing in customer environments, validate findings identified by its AI agents, and help improve its product and research capabilities.

This is a mid-level position for someone who enjoys practical offensive-security work and wants to take on more responsibility while working alongside experienced security researchers and engineers.

You will investigate real vulnerabilities, test their exploitability and determine whether findings represent genuine, reproducible security issues. Practical ability is valued more highly than certifications.

Key Responsibilities

• Conduct penetration tests across customer applications, APIs and infrastructure, with support on more complex engagements.
• Support red-team exercises by investigating attack paths, testing weaknesses and contributing to exploitation.
• Manually validate findings generated by AI agents, distinguishing reproducible vulnerabilities from false positives.
• Develop clear proof-of-concept exploits demonstrating exploitability, realistic impact and the conditions required for an attack.
• Produce concise technical reports containing evidence and practical remediation recommendations.
• Collaborate with engineers to improve agent behaviour, testing coverage and the quality of findings.
• Turn discoveries into scripts, repeatable test cases and research inputs.
• Work carefully within agreed testing scopes, communicate clearly and exercise sound judgement when working in customer environments.

Requirements

• Hands-on experience in penetration testing, an internal offensive-security team or substantial bug-bounty research.
• A solid understanding of common vulnerabilities and the ability to exploit them manually, including access-control issues, authentication weaknesses and injection vulnerabilities.
• Confidence testing web applications and APIs, alongside experience with infrastructure or cloud environments.
• Familiarity with tools such as Burp Suite and Nmap, including the ability to assess and challenge their results.
• Ability to write or adapt Python scripts to automate tasks and support security testing.
• Strong written communication skills, with the ability to explain findings, reproduce vulnerabilities and demonstrate their impact.
• Curiosity, persistence and a willingness to seek help when an unfamiliar problem requires a different approach.

Desirable Experience

Experience in any of the following areas would be advantageous:

• Active Directory.
• Privilege escalation.
• Cloud security.
• Adversary emulation.
• Exploit development.
• Public security research, useful tooling or technical write-ups.

Candidates do not need experience in every area to apply.

Certifications and AI Experience

Certifications such as OSCP are welcome but not mandatory. The company is more interested in how candidates investigate targets, reason through vulnerabilities and demonstrate their impact.

Previous AI experience is not required. An interest in how autonomous agents can support offensive-security work is welcomed.

What the Company Offers

• The opportunity to influence the development of an AI-powered security product directly through practical testing.
• Close collaboration with engineers building autonomous security agents.
• Exposure to real customer environments and deeper technical investigations.
• Opportunities to develop offensive-security skills alongside experienced colleagues.
• Meaningful responsibility within a small team, with the opportunity to help shape the future of automated security testing.

Pay: £60,000.00-£75,000.00 per year

Work Location: Hybrid remote in London