AI Security Penetration Tester (Remote Contract)

Alignerr; Amsterdam; On-site; EUR 83,000 - 165,000; Full time

Job summary

Alignerr is seeking a Cybersecurity Penetration Testing Expert (AI Security) to proactively attack and stress-test AI-powered systems. This fully remote hourly contract role emphasizes autonomous, task-based engagements and flexible scheduling.

You will conduct comprehensive assessments across applications, APIs, and infrastructure, focusing on prompt injection, model manipulation, data poisoning, and authentication weaknesses, while delivering actionable remediation guidance.

Qualifications

• Proven experience performing pentests on AI-enabled apps, APIs, and infrastructures.
• Strong understanding of offensive security principles and testing methodologies (OWASP, PTES).
• Familiarity with AI/ML security concepts, prompt injection, data poisoning, and jailbreaks.

Responsibilities

• Conduct penetration tests against AI-powered applications, APIs, and infrastructure.
• Identify weaknesses in AI/ML pipelines and authenticate/privilege exploitation paths.
• Perform web, network, and API security assessments using standard tools and methods.
• Document findings with severity, evidence, and remediation guidance.
• Stay current with AI security threats and improve testing methodologies.

Skills

Penetration testing

OWASP

MITRE ATT&CK

Python scripting

Threat modelling

Adversary simulation

Tools

Burp Suite

Metasploit

Nmap

Kali Linux

Job description

Alignerr is seeking a Cybersecurity Penetration Testing Expert (AI Security) to proactively attack and stress-test AI-powered systems. This fully remote hourly contract role emphasizes autonomous, task-based engagements and flexible scheduling.

You will conduct comprehensive assessments across applications, APIs, and infrastructure, focusing on prompt injection, model manipulation, data poisoning, and authentication weaknesses, while delivering actionable remediation guidance.