Job Title

Work Location: Toronto, Ontario, Canada Hours: 37.5 Line Of Business: Technology Solutions Pay Details: $114,000 - $136,800 CAD This role is temporarily eligible for a pay premium above the posted salary range that is reassessed annually. You are encouraged to have an open dialogue with your recruiter who can provide more specific pay details for this role. 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. Our compensation policies and practices have been designed to allow colleagues to progress through the salary range over time as they progress in their role. The base pay actually offered may vary based upon the candidate''''s skills and experience, job-related knowledge, geographic location, and other specific business and organizational needs. As a candidate, you are encouraged to ask compensation related questions and have an open dialogue with your recruiter who can provide you more specific details for this role. Job Description Role Summary: The Information Security Specialist AI Penetration Tester is responsible for conducting advanced offensive security testing across AI/ML systems, LLM integrations, GenAI platforms, and associated infrastructure. This role serves as a subjectmatter expert in AI/LLM security, partnering with engineering, cyber, cloud, and architecture teams to identify vulnerabilities, improve controls, and ensure safe and compliant deployment of AI capabilities across the enterprise. Responsibilities AI/LLM Offensive Security & Vulnerability Testing Conduct Penetration Tests: Design and execute comprehensive penetration tests targeting AI/ML models, LLM applications, model pipelines, retrieval systems, data agents, and AI-enabled business workflows. AI/LLM Vulnerability Analysis: Identify vulnerabilities such as jailbreaking, prompt injection, model extraction, adversarial ML attacks, data poisoning, RAG bypasses, and safety guardrail circumvention. Tooling & Automation: Evaluate and develop tooling (including internal utilities and opensource frameworks) to automate and scale AI/LLM security testing. Security Architecture, Hardening & Risk Assessment Assess Security Posture: Analyze training data governance, guardrail design, inference endpoints, system prompts, agent autonomy, model monitoring, and modelops pipelines. Risk Assessments: Perform security and safety risk analyses on new and existing AI/ML deployments, including cloudbased services, APIs, model marketplaces, and thirdparty LLM integrations. Model Supply Chain Security: Assess AI supply chain risks, dependency integrity, and alignment with enterprise standards and regulatory obligations. Documentation, Reporting & Communication Report Findings: Deliver clear, actionable findings to both technical and nontechnical stakeholders. Produce detailed reporting including: Executive summaries Technical proofofconcepts Prioritized remediation recommendations Stakeholder Engagement: Collaborate with Engineering, Data Science, Cloud, Cyber Defense, Architecture, and Risk to remediate findings and improve AI security posture. Governance, Standards & Continuous Improvement Develop Best Practices: Contribute to organizationwide AI security standards, policies, control objectives, and hardening practices. Regulatory Compliance: Ensure AI penetration testing aligns with regulatory, privacy, model safety, and internal policy requirements. Continuous Learning: Maintain deep expertise in emerging AI threats, industry frameworks, evaluation methodologies, and global safety standards. Incident Response & Audit Support Participate in AI/MLrelated security incident investigations, providing subjectmatter expertise on root cause analysis and exploitation methods. Support audit preparation and assist in drafting management responses, remediation plans, and risk treatment documentation. Requirements Technical Skills: 5+ years in application security or penetration testing, with handson experience in AI/ML environments preferred. 7+ years of experience using penetration testing tools (Metasploit, Burp Suite, Nmap, Kali, etc.). Strong knowledge of AI/LLM vulnerabilities including OWASP Top 10 for LLMs, adversarial attacks, prompt injection, and model safety testing frameworks. Familiarity with scripting and automation (Python preferred), model interrogation techniques, and cloudnative AI services (Azure, AWS, GCP). Core Competencies: Strong analytical and problemsolving abilities with high attention to detail. Excellent written and verbal communication skills for diverse stakeholder groups. Demonstrated understanding of ethical hacking principles and responsible AI use. Preferred Qualifications: Experience penetration testing AI/LLM platforms, cloud workloads, and PCIscoped 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. Le spcialiste en scurit de linformation Testeur dintrusion en IA Responsabilits similaires aux sections cidessus traduites en franais : Responsabilits Raliser des tests dintrusion : Concevoir et excuter des tests dintrusion complets visant les modles IA/ML, les applications LLM, les pipelines de modles, les systmes de rcupration augmente (RAG), les agents de donnes ainsi que les processus daffaires intgrant lIA. Analyse des vulnrabilits IA/LLM : Dceler des vulnrabilits telles que le contournement des protections (jailbreaking), linjection de requtes (prompt injection), lextraction de modles, les attaques adversariales en apprentissage automatique, lempoisonnement des donnes, le contournement des mcanismes RAG et la neutralisation des gardefous de scurit. Outillage et automatisation : valuer, dvelopper et amliorer des outils (incluant des utilitaires internes et des cadres open source) afin dautomatiser et de faire voluer les activits de tests de scurit IA/LLM. Architecture de scurit, durcissement et valuation des risques valuation de la posture de scurit : Analyser la gouvernance des donnes dentranement, la conception des gardefous, les points daccs dinfrence, les invites systme, lautonomie des agents, la surveillance des modles et les pipelines MLOps. valuations des risques : Effectuer des analyses de risques en matire de scurit et de sret pour les dploiements IA/ML nouveaux et existants, y compris les services infonuagiques, les API, les places de march de modles et les intgrations LLM de fournisseurs tiers. Scurit de la chane dapprovisionnement des modles : valuer les risques lis la chane dapprovisionnement de lIA, lintgrit des dpendances ainsi que lalignement avec les normes organisationnelles et les exigences rglementaires. Documentation, rapports et communication Production de rapports : Prsenter des constats clairs, prcis et exploitables des parties prenantes techniques et non techniques. Produire une documentation complte comprenant notamment : des rsums destins la haute direction ; des preuves de concept techniques ; des recommandations de remdiation priorises. Collaboration avec les parties prenantes : Travailler en troite collaboration avec les quipes dingnierie, de science des donnes, dinfonuagique, de cyberdfense, darchitecture et de gestion des risques afin de corriger les vulnrabilits et damliorer la posture globale de scurit de lIA. Gouvernance, normes et amlioration continue Dveloppement des meilleures pratiques : Contribuer llaboration et lvolution des normes, politiques, objectifs de contrle et pratiques de durcissement en matire de scurit de lIA lchelle de lorganisation. Conformit rglementaire : Veiller ce que les activits de tests dintrusion en IA respectent les exigences rglementaires, les obligations en matire de protection des renseignements personnels, la sret des modles et les politiques internes. Veille et apprentissage continus : Maintenir une expertise approfondie sur les menaces mergentes lies lIA, les cadres de rfrence du secteur, les mthodologies dvaluation et les normes internationales de sret. Soutien aux incidents et aux audits Participer aux enqutes lies aux incidents de scurit touchant lIA/ML, en fournissant une expertise spcialise sur lanalyse des causes fondamentales et les techniques dexploitation. Soutenir la prparation des audits et contribuer la rdaction des rponses de la direction, des plans de correction et de la documentation relative au traitement des risques. Exigences (Franais) Minimum de 5 ans dexprience en scurit applicative ou en tests dintrusion, avec une exprience pratique en environnements IA/ML considre comme un atout important. Minimum de 7 ans dexprience avec des outils de tests dintrusion (Metasploit, Burp Suite, Nmap, Kali, etc.). Excellente connaissance des vulnrabilits propres aux IA/LLM, incluant lOWASP Top 10 pour les LLM, les attaques adversariales, linjection de requtes et les cadres dvaluation de la sret des modles. Exprience en scripting et en automatisation (Python privilgi), en techniques dinterrogation de modles et en services dIA natifs de linfonuagique (Azure, AWS, GCP). Comptences cls (Franais) Solides aptitudes analytiques et de rsolution de problmes, avec un souci marqu du dtail. Excellentes habilets de communication crite et orale, adaptes des publics varis. Comprhension dmontre des principes de piratage thique et de lutilisation responsable de lIA. Qualifications Souhaites (Franais) Exprience en tests dintrusion de plateformes IA/LLM, de charges de travail infonuagiques et denvironnements assujettis aux exigences PCI. Connaissance des cadres et normes de scurit (NIST AI RMF, OWASP LLM/ML, ISO 42001, MITRE ATLAS). Certifications pertinentes : OSCP, CEH, GPEN, CISSP ou certifications en scurit de lIA/ML. Exprience en soutien aux audits, aux examens de conformit et aux activits de rponse aux incidents. Who We Are TD is one of the world''''s leading global financial institutions and is the fifth largest bank in North America by branches/stores. Every day, we strive to make every interaction, product, and experience remarkably human and refreshingly simple for over 27 million households and businesses in Canada, the United States and around the world. More than 95,000 TD colleagues bring their skills, talent, and creativity to foster deeper relationships, ensure disciplined execution, and build a simpler, faster banking experience. TD is deeply committed to being a leader in client experience, that is why we believe that all colleagues, no matter where they work, are client facing. Together, we are reimagining what banking can be for our clients, colleagues and communities. Our Total Rewards Package Our Total Rewards package reflects the investments we make in our colleagues to help them and their families achieve their financial, physical, and mental wellbeing goals. Total Rewards at TD includes a base salary, variable compensation, and several other key plans such as health and wellbeing benefits, savings and retirement programs, paid time off, banking benefits and discounts, career development, and reward and recognition programs. Learn more Additional Information Were delighted that youre considering building a career with TD. Through regular development conversations, training programs, and a competitive benefits plan, were committed to providing the support our colleagues need to thrive both at work and at home. Please be advised that this job opportunity is subject to provincial regulation for employment purposes. It is imperative to acknowledge that each province or territory within the jurisdiction of Canada may have its own set of regulations, requirements. Colleague Development If youre interested in a specific career path or are looking to build certain skills, we want to help you succeed. Youll have regular career, development, and performance conversations with your manager, as well as access to an online learning platform and a variety of mentoring programs to help you unlock future opportunities. If youre passionate about helping clients and building deep, lasting relationships, TD offers diverse career paths where you can grow your expertise and make a meaningful impact. We''''re committed to your success and foster a respectful workplace where diverse perspectives are valued, everyone has fair opportunities to grow, and you can unlock your full potential to achieve your career goals. Here at TD, we hire and develop the best. Training & Onboarding We will provide training and onboarding sessions to ensure that youve got everything you need to succeed in your new role. Interview Process Well reach out to candidates of interest to schedule an interview. We do our best to communicate outcomes to all applicants by email or phone call. Accommodation Your accessibility is important to us. Please let us know if youd like accommodations (including accessible meeting rooms, captioning for virtual interviews, etc.) to help us remove barriers so that you can participate throughout the interview process. Language Requirement (Quebec Only) Sans Objet #J-18808-Ljbffr