AI Security Engineer: Offensive AI Pen Tester

MWEK Solutions DMCC

England

Hybrid

GBP 54,000 - 66,000

Full time

8 days ago

Application generator

Stand out for this role — generate a tailored resume and cover letter in about a minute.

Get past ATS filters

Job summary

MWEK Solutions DMCC in Berkshire is seeking an AI Security Tester to simulate real-world attacks on AI/ML systems, stress-test model guardrails, and protect data privacy. Hybrid role with occasional onsite travel; permanent position up to £60K.

You will identify vulnerabilities, document findings, and collaborate with security teams to harden deployments. The ideal candidate has 5+ years in offensive cybersecurity and at least 2 years focused on AI/ML security, with strong Python/Java and ML

Qualifications

5+ years in offensive cybersecurity (AppSec, pen testing, red teaming).
Minimum 2 years focused on AI/ML security.
Strong Python and Java programming skills.
Hands-on experience with ML frameworks such as PyTorch or TensorFlow.
Familiarity with AI tooling (LangChain, LlamaIndex, red-teaming toolkits).
Proven ability to assess and secure AI systems end-to-end.

Responsibilities

Conduct adversarial testing to challenge AI model safety and guardrails.
Perform penetration testing and fuzzing of AI systems.
Identify risks such as data poisoning, model evasion, hallucinations and bias.
Validate data privacy controls, including PII handling and encryption.
Simulate attack scenarios and exploit attempts.
Document vulnerabilities, unexpected behaviours and evidence in lower environments.
Analyse threat vectors and recommend mitigation strategies.