Senior AI Red Team Developer
- Toronto, ON, Canada
Contract
Applications open in a new tab.
Job details
- Job type
- Contract
- Apply by
- Experience
- Experience: 6–8 years overall, including 1+ year of hands-on AI/LLM Red Teaming experience
- Posting language
- English
- Posted
Original job description
Role: Senior AI Red Team Testing Specialist
Work model: Onsite (Toronto Downtown)
Hiring Mode: Contract
Please look for candidates with a strong cybersecurity / offensive security background combined with practical experience testing LLM and GenAI solutions.
Experience: 6–8 years overall, including 1+ year of hands-on AI/LLM Red Teaming experience
Key skills: AI Red Teaming, prompt injection, jailbreaking, adversarial ML, guardrail bypass, vulnerability lifecycle, penetration testing, and application security
More about this job
Responsibilities
Test large language model and generative AI solutions for security vulnerabilities, including prompt injection, jailbreaks, adversarial attacks, and guardrail bypasses. Apply offensive security and penetration-testing practices across the vulnerability lifecycle.
Requirements
Candidates should have 6–8 years of overall experience, including at least one year of hands-on AI/LLM red teaming. A strong cybersecurity or offensive security background and practical experience testing LLM and generative AI solutions are required.
Skills
- AI Red Teaming
- Prompt Injection
- Jailbreaking
- Adversarial Machine Learning
- Guardrail Bypass
- Vulnerability Lifecycle
- Penetration Testing
- Application Security
- Cybersecurity
- Offensive Security
- Large Language Models
- Generative AI Testing
Visa sponsorship
Not detected in the job text
Categories
- Security & Safety
- Technology
- Software
Keywords
- AI Red Teaming
- LLM Red Teaming
- Large Language Models
- Generative AI
- Prompt Injection
- Jailbreaking
- Adversarial Machine Learning
- Guardrail Bypass
- Vulnerability Lifecycle
- Penetration Testing
- Application Security
- Cybersecurity
- Offensive Security