Senior Developer
- Toronto, ON, Canada
$60 to $65 CAD / hour · Contract
Applications open in a new tab.
Job details
- Pay
- $60 to $65 CAD / hour
- Job type
- Contract
- Apply by
- Posting language
- English
- Posted
Original job description
Role: Senior Developer / Senior Designer
Location: Toronto, Canada
Duration: Long Term Contract
Role Overview
We are looking for an experienced Senior Developer / Senior Designer with expertise in AI Red Teaming and security testing. The candidate will be responsible for performing adversarial testing of Large Language Models (LLMs) using specialized AI Red Teaming tools to identify vulnerabilities, simulate potential attacks, evaluate security guardrails, and recommend risk-based remediation.
The ideal candidate should have hands-on experience in AI security testing, application security, and vulnerability assessment across the AI development lifecycle.
Key Responsibilities
- Execute AI Red Teaming activities to identify security vulnerabilities in LLM-based applications.
- Perform adversarial testing, including prompt injection, jailbreaking, and guardrail bypass techniques.
- Simulate real-world attacks against AI models using specialized AI Red Teaming tools.
- Identify vulnerabilities in LLM applications and assess associated security risks.
- Conduct penetration testing and application security assessments.
- Evaluate AI model safety, security controls, and guardrail effectiveness.
- Document findings, prepare vulnerability reports, and recommend remediation strategies.
- Collaborate with AI engineers, developers, and security teams to strengthen AI security.
- Support vulnerability tracking and remediation throughout the AI lifecycle.
Required Skills & Qualifications
- 6–8 years of overall experience in software development, security engineering, or application security.
- Minimum 1+ year of hands-on experience in AI security or AI Red Teaming.
- Strong understanding of LLM security and adversarial testing techniques.
- Hands-on experience with:
- Prompt Injection and Jailbreaking
- Adversarial Machine Learning
- AI Guardrail Bypass Testing
- LLM Vulnerability Assessment
- AI Red Teaming Tools
- Vulnerability Lifecycle Management
- Penetration Testing
- Application Security
- Understanding of AI/LLM security risks, attack vectors, and mitigation techniques.
- Strong analytical, problem-solving, and security assessment skills.
More about this job
Responsibilities
Conduct adversarial testing and penetration testing of LLM-based applications to identify vulnerabilities, simulate attacks, and evaluate model safety and security controls. Document findings, recommend risk-based remediation, and collaborate with engineering and security teams to track and address vulnerabilities throughout the AI lifecycle.
Requirements
Requires 6–8 years of experience in software development, security engineering, or application security, including at least one year of hands-on AI security or AI Red Teaming experience. Candidates should understand LLM security risks and adversarial testing techniques and have experience with prompt injection, jailbreaking, guardrail bypass testing, vulnerability assessment, and penetration testing.
Skills
- AI Red Teaming
- LLM Security
- Prompt Injection Testing
- Jailbreaking
- Adversarial Machine Learning
- AI Guardrail Bypass Testing
- LLM Vulnerability Assessment
- Penetration Testing
- Application Security
- Vulnerability Assessment
- Security Risk Assessment
- AI Security Testing
- Security Reporting
- Remediation Planning
Visa sponsorship
Not detected in the job text
Categories
- Security & Safety
- Technology
- Software
Keywords
- AI Red Teaming
- Large Language Models
- LLM Security
- Prompt Injection
- Jailbreaking
- Adversarial Testing
- Adversarial Machine Learning
- AI Guardrails
- Guardrail Bypass
- AI Security Testing
- LLM Vulnerability Assessment
- Vulnerability Assessment
- Penetration Testing
- Application Security
- Security Engineering
- AI Model Safety
- Security Controls
- Attack Simulation
- Risk Assessment
- Risk-Based Remediation
- Vulnerability Reporting
- AI Development Lifecycle