About this role
Read the essentials first, then expand the complete employer description for more detail.
Connect role summary
Automatically condensed from the published description; check the original employer listing before applying.
- Accountabilities: Tailor guardrails to each partner’s policies, regulations, risk appetite, and languages, defining what the AI may do, what it must refuse, and when it hands off to a human. Design protections for sensitive data and…
Read the complete job description ⌄
Accountabilities: Tailor guardrails to each partner’s policies, regulations, risk appetite, and languages, defining what the AI may do, what it must refuse, and when it hands off to a human. Design protections for sensitive data and actions, including data masking, identity checks, and customer consent before any change to a booking or payment. Tune guardrails to stop real risks without blocking legitimate customers. Red-team every deployment before launch and after significant changes, testing for jailbreaks, prompt injection, data leakage, unauthorized actions, and social engineering. Build and maintain automated adversarial test suites that run continuously, in every language a partner serves, and turn findings into fixes and regression tests with engineering. Lead partner security questionnaires, architecture reviews, and AI or model-risk reviews, and respond to partner penetration-test findings. Document how the AI handles data, access, and decisions in terms a regulator or auditor would accept. Own the go-live checklist for each deployment, covering functional, regression, safety, and load testing, sign-off criteria, and rollback plans. Extend automated testing across products so every model, prompt, or configuration change is tested before it reaches customers. Coordinate user acceptance testing with partners and close out issues before launch. Lead the security and privacy side of partner data access for forward-deployed teams, including data-sharing agreements, IT security reviews, and secure access to partner systems, including on-premise ones. Define how partner data is handled, stored, separated, and deleted across deployments and model training, and ensure those rules are followed. Monitor live deployments for quality, reliability, abuse, and safety failures, setting up dashboards and alerting with engineering. Lead the response to safety or security incidents, with clear communication to the partner throughout. Work closely with Research, Product, and Security so new models and features ship with security built in, and turn each deployment into reusable guardrails, tests, and documentation. Requirements 5+ years across security engineering, application security, AI safety, quality engineering, or site reliability, with hands-on work keeping production systems secure and running. Hands-on red-teaming of LLM applications or agents, including jailbreaks, prompt injection, data exfiltration, and tool and permission abuse, using findings to close real gaps. Experience designing and tuning guardrails or safety controls for an LLM-based product, with evidence they stopped real risk without hurting customer experience. Experience representing a vendor in enterprise security reviews, including questionnaires, architecture reviews, and penetration-test remediation, and securing sign-off from partner security teams. Ownership of testing and release quality for a production system, from automated test suites and release gates to load testing and rollback, including holding a launch when it was not ready. Strong Python skills and the ability to build automated test harnesses and tooling that make adversarial and regression testing continuous. Experience securing or operating systems for travel or financial services companies (airlines, hotels, OTAs, banks, or payments companies), with an understanding of fraud, account-takeover, and payment risks. Confidence explaining risk clearly to engineers, partner security teams, and non-technical executives, and pushing back when a deployment is not ready. Willingness to travel for launches and reviews. Nice to have: Security or risk work in regulated industries such as banking, payments, or aviation, or model-risk and AI governance reviews at a financial institution. Nice to have: Familiarity with security and AI risk frameworks such as the OWASP Top 10 for LLM applications, SOC 2, ISO 27001, PCI DSS, and NIST AI RMF. Nice to have: Data privacy and governance work, such as data-sharing agreements, secure access to customer systems, or GDPR and similar regimes (e.g., Quebec’s Law 25). Nice to have: Observability and incident management experience, such as Datadog, on-call, and post-mortems. Nice to have: Multilingual safety testing, or voice and conversational AI security. Nice to have: Forward-deployed or customer-facing security engineering experience. Benefits Total annual compensation of CA$400,000 to CA$520,000, including base salary (CA$360K–CA$425K), equity (options), a sign-on bonus, and other potential incentives. Pre-IPO equity upside with a well-funded, proven company. 100% employer-paid group insurance premiums, plus life, short-term, and long-term disability coverage. Health spending account covering eligible medical and dental expenses. Telemedicine access for employees and dependents, anytime and anywhere. RRSP plan with automatic pre-tax payroll contributions. Very generous parental leave, well above industry standards. Unlimited paid time off. Travel stipend. Remote work with on-demand co-working space access and a work-from-home stipend. Entrepreneurial culture with open communication with leadership and small, dynamic teams. How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1
- LOCATION
- Remote · Canada
- WORK MODE
- Remote
- JOB TYPE
- Full-time
- POSTED
- Nov 20, 2026
Source: Jobgether Careers