Job Responsibilities:

Design and execute system-level and module-level test cases to ensure the correctness and performance of AI security firewall features, including prompt filtering, content moderation, and response policy enforcement. Build and manage test datasets to simulate normal, abnormal, and adversarial prompts; evaluate the model’s ability to detect and defend against potential attacks such as prompt injection or misuse. Validate the overall effectiveness of model integration, including key metrics such as detection accuracy, false positive rate (FPR), and false negative rate (FNR), while continuously improving test coverage. Collaborate closely with R&D, security, and product teams to translate AI security requirements into verifiable test scenarios; participate in bug reproduction and root cause analysis. Set up test environments and conduct ongoing regression and performance/stress testing. Contribute to building hybrid local/cloud-based testing platforms; be proficient in containerized deployment (Docker/Kubernetes) to support flexible testing across multiple model versions and security policy configurations. Stay up to date with industry standards and best practices related to LLM/Generative AI security (e.g., OWASP Top 10 for LLMs), and incorporate relevant threat simulations and validations into test plans.

Job Requirements:

Familiarity with common AI security threats such as prompt injection, output manipulation, data poisoning, and hallucination; hands-on testing experience in these areas is preferred. Proficiency in Python programming, with experience using testing frameworks such as pytest,  unittest, or others for automated testing. Strong knowledge of RESTful API testing methodologies, and an understanding of model inference interfaces, vector databases, and embedding workflows. Experience with containerization and cloud platforms (e.g., Docker, Kubernetes, AWS, GCP, Azure), with the ability to build and manage test environments and perform resource-level debugging. Excellent analytical and communication skills, with the ability to drive issue resolution and quality improvement across cross-functional teams. Prior experience in testing AI/ML systems, model deployments, or security-related products is highly desirable.

The Canada base salary range for this full-time position is expected to be between $118,000 - $144,000 annually.  Wage ranges are based on various factors including the labour market, job type, and job level.  Exact salary offers will be determined by factors such as the candidate’s subject knowledge, skill level, qualifications, and experience. 

 

Fortinet strives to provide you and your family with a comprehensive benefits package. Benefits eligibility starts on your first day of hire and comprises of 100% company paid medical, dental, and vision coverage, including a Health Spending Account and a Personal Spending Account that gives you flexibility to spend where you need it the most. Our Employee & Family Assistance Plan (EFAP) offers you and your family access to various services like counseling, legal advice, mental health resources etc. We also provide critical illness, disability, and life insurance, as well as a Group Registered Retirement Savings Plan (RRSP) with a company match to help you save faster for retirement. We offer competitive Paid Time Off and flexible leave policies, including paid health days, to help you take care of yourself and your family members.

All roles are eligible to participate in the Fortinet equity program.  Bonus eligibility is reviewed at time of hire and annually at the Company’s discretion. 

Why Join Us:

We encourage candidates from all backgrounds and identities to apply. We offer a supportive work environment and a competitive Total Rewards package to support you with your overall health and financial well-being. Embark on a challenging, enjoyable, and rewarding career journey with Fortinet. Join us in bringing solutions that make a meaningful and lasting impact to our 660,000+ customers around the globe.