A.I. Adversarial Testing Engineer

The Toronto-Dominion Bank (Canada); Toronto; Hybrid; CAD 91,000 - 137,000; Full time

Job summary

An established industry player is seeking an A.I. Adversarial Testing Engineer to enhance the security of AI models. In this pivotal role, you will develop and implement innovative testing tools to evaluate the resilience of AI systems against adversarial attacks. Your expertise will guide red teaming exercises and collaboration with industry experts to identify vulnerabilities. This position offers a unique opportunity to work at the intersection of analytics and artificial intelligence, contributing to the advancement of robust AI defenses. Join a dynamic team dedicated to pioneering solutions in the AI landscape and make a significant impact in the field.

Qualifications

• 5+ years in IT with a focus on AI and adversarial experience.
• Strong programming skills in Python and C++ are essential.
• In-depth knowledge of adversarial AI and cybersecurity frameworks.

Responsibilities

• Develop and implement test tools for AI system resilience.
• Conduct red teaming exercises to assess AI security.
• Collaborate with experts to identify threats and vulnerabilities.

Skills

Python

C++

Machine Learning

Adversarial AI Concepts

Penetration Testing

Ethical Hacking

Data Analysis

Communication Skills

Education

Bachelor’s degree in Computer Science

Master’s degree in Computer Engineering

Tools

Azure Cloud

AI Testing Tools

Job description

A.I. Adversarial Testing Engineer

Apply: Remote type Hybrid, Locations: Toronto, Ontario, Time type: Full time, Posted: 15 Days Ago, End Date: May 30, 2025

Work Location: Toronto, Ontario, Canada

Hours: 37.5

Line of Business: Analytics, Insights, & Artificial Intelligence

Pay Details: $91,200 - $136,800 CAD

TD is committed to providing fair and equitable compensation opportunities to all colleagues. Growth opportunities and skill development are defining features of the colleague experience at TD.

Job Description:

Responsibilities:

• Develop and implement test tools that evaluate the resilience of an AI-enabled system to adversarial attacks.
• Conduct red teaming exercises to assess the security of AI models and AI-enabled systems.
• Collaborate with industry subject matter experts to identify potential threats and vulnerabilities.
• Build and maintain tools, scripts, and frameworks to automate evaluation and resilience of AI-enabled systems.
• Work on solutions to enhance defense mechanisms for AI models.
• Generate comprehensive reports and documentation of red teaming exercises.
• Stay up-to-date with the latest advancements in AI.
• Collaborate with cross-functional teams to provide insights and recommendations for improving adversarial AI defenses.

Required Skills and Qualifications:

• Bachelor’s/Master’s degree in computer science, computer engineering, or relevant field.
• Minimum 5+ years in IT:
• 2+ Years in AI
• 3+ Years Azure Cloud Engineer
• 3+ years in Adversary experience
• Strong programming skills in languages like Python and C++.
• Proficiency in machine learning and AI technologies.
• Experience with evaluating AI models and creating test harnesses for offensive use.
• In-depth knowledge of adversarial AI concepts and defensive measures.
• Experience with penetration testing and ethical hacking.
• Familiarity with adversarial AI and cybersecurity frameworks and standards.
• Experience with Model Evasion, Extraction, Inversion, Poisoning attacks, and LLM Prompt injection.
• Strong communication skills to articulate findings and recommendations effectively.
• Demonstrated expertise in Adversarial AI threat landscape.
• Experience with Enterprise Data Lakes and data analysis tools.