This role involves conducting advanced offensive security testing on AI/ML systems, including LLM integrations and GenAI platforms. The specialist acts as a subject matter expert in AI/LLM security, collaborating with various teams to identify vulnerabilities, enhance controls, and ensure secure and compliant AI deployments across the enterprise.
Design and execute comprehensive penetration tests targeting AI/ML models, LLM applications, model pipelines, retrieval systems, data agents, and AI-enabled business workflows.,Identify vulnerabilities such as jailbreaking, prompt injection, model extraction, adversarial ML attacks, data poisoning, RAG bypasses, and safety guardrail circumvention.,Evaluate and develop tooling (including internal utilities and open‑source frameworks) to automate and scale AI/LLM security testing.,Analyze training data governance, guardrail design, inference endpoints, system prompts, agent autonomy, model monitoring, and model‑ops pipelines.,Perform security and safety risk analyses on new and existing AI/ML deployments, including cloud‑based services, APIs, model marketplaces, and third‑party LLM integrations.,Assess AI supply chain risks, dependency integrity, and alignment with enterprise standards and regulatory obligations.,Deliver clear, actionable findings to both technical and non‑technical stakeholders, including executive summaries, technical proof‑of‑concepts, and prioritized remediation recommendations.,Collaborate with Engineering, Data Science, Cloud, Cyber Defense, Architecture, and Risk to remediate findings and improve AI security posture.,Contribute to organization-wide AI security standards, policies, control objectives, and hardening practices.,Ensure AI penetration testing aligns with regulatory, privacy, model safety, and internal policy requirements.,Maintain deep expertise in emerging AI threats, industry frameworks, evaluation methodologies, and global safety standards.,Participate in AI/ML–related security incident investigations, providing subject-matter expertise on root cause analysis and exploitation methods.,Support audit preparation and assist in drafting management responses, remediation plans, and risk treatment documentation.
Experience penetration testing AI/LLM platforms, cloud workloads, and PCI-scoped environments.,Knowledge of security frameworks (NIST AI RMF, OWASP LLM/ML, ISO 42001, MITRE ATLAS).,Relevant certifications: OSCP, CEH, GPEN, CISSP, or AI/ML security certifications.,Experience supporting audits, compliance reviews, and incident response activities.
This job opportunity is subject to provincial regulation for employment purposes.
The Toronto-Dominion Bank and its subsidiaries are collectively known as TD Bank Group, one of the largest banks in North America. TD provides a wide range of personal, commercial, and investment banking products and services to over 27 million customers globally. Headquartered in Toronto, Canada, the bank operates through key segments including Canadian Retail, U.S. Retail, and Wholesale Banking.
BerryMap uses cookies to provide essential features, analyze usage, and improve your experience. You can customize your preferences below.