Staff Security Engineer, Enterprise AI
New
A
AffirmFinancial Technology
Remote Canada; open only to candidates residing in Alberta, British Columbia, Manitoba, New Brunswick, Newfoundland and Labrador, Nova Scotia, Ontario, Prince Edward Island, or Saskatchewan.Full-TimeStaff
SalaryCAN base pay range per year: $181,000 - $241,000 CAD.
Apply NowOpens the employer's application page
Job Details
- Required Skills
- AWSPythonKubernetesOAuthTerraformLLM
Requirements
- Seasoned experience in designing, evaluating, and maintaining security architecture for AI/LLM-based systems.
- Deep expertise in enterprise security systems, processes, and controls.
- Proven experience threat modeling AI applications against frameworks like the OWASP Top 10 for LLM Applications.
- Hands-on experience securing agentic systems, tool-calling frameworks (MCP), and agent-to-tool trust boundaries.
- Experience building AI governance artifacts including acceptable use policies and data-handling standards.
- Ability to evaluate AI capabilities within SaaS platforms like Notion AI, Slack AI, and Google Workspace AI.
- Strong proficiency in building security tooling and guardrails using Python.
- Experience deploying cloud services and policy-as-code using Terraform or similar Infrastructure as Code tools.
- Familiarity with Kubernetes and AWS environments.
- Strong understanding of LLM/Agentic architecture, RAG, embeddings, and fine-tuning.
- Knowledge of authentication/authorization models (OAuth2, SAML, service-account identities).
- Effective leadership and communication skills for cross-functional collaboration across Security, Engineering, and Legal teams.
Responsibilities
- Lead and continuously improve the enterprise AI security review process for internal AI tools and agentic systems.
- Perform threat modeling on AI/LLM systems and data flows to address risks like prompt injection, data poisoning, and unauthorized tool access.
- Review source code, system prompts, and tool configurations to ensure security requirements are met during the design phase.
- Design and deploy security guardrails, Python-based tooling, and policy-as-code to enforce AI security and permission boundaries.
- Evaluate third-party AI SaaS vendor capabilities and conduct AI-specific risk assessments.
- Identify emerging AI security vulnerabilities and develop mitigation strategies and incident response playbooks.
- Advise technical and executive stakeholders on AI security practices and translate research into practical organizational controls.
View Full Description & ApplyYou'll be redirected to the employer's site
