Senior Security Developer – AI Red Teaming (Pen Testing)

About the role

We are looking for a Senior Security Developer to lead AI Red Teaming initiatives while maintaining a strong focus on traditional penetration testing and application security. The position is based in Toronto with a hybrid work model (three days onsite).

Key responsibilities

• Conduct AI/LLM Red Teaming, including prompt injection, jailbreaking, and guardrail bypass testing.
• Perform penetration testing and red‑team engagements across web, cloud, and internal applications.
• Design and execute adversarial machine‑learning tests against AI systems.
• Identify, assess, and document security vulnerabilities throughout their lifecycle.
• Provide risk assessments and actionable remediation recommendations to technical and business stakeholders.
• Produce detailed technical reports and present findings to diverse audiences.

Required profile

• 6–8+ years of experience in penetration testing, red teaming, or application security.
• At least 1 year of hands‑on experience with AI/LLM Red Teaming.
• Deep knowledge of prompt injection, jailbreaking, adversarial ML, and guardrail bypass techniques.
• Proven ability to manage the full vulnerability lifecycle from discovery to remediation.
• Excellent communication skills for both technical and non‑technical stakeholders.

Required skills

• Penetration Testing
• Red Teaming
• Application Security
• AI/LLM Red Teaming
• Prompt Injection
• Jailbreaking
• Adversarial Machine Learning
• Security testing tools