1 day ago
Remote, CanadaSenior
Base Salary
$360k - $425k/yr
Responsibilities
- Tailor AI guardrails to partner policies, regulations, risk tolerances, languages, refusal rules, and human-handoff requirements.
- Design protections for sensitive data and high-impact actions, including masking, identity checks, and customer consent for booking and payment changes.
- Red-team AI deployments for jailbreaks, prompt injection, data leakage, unauthorized actions, social engineering, and related risks.
- Build and maintain automated adversarial, regression, functional, safety, and load-testing suites and release gates.
- Translate security findings into engineering fixes and durable regression tests.
- Lead partner security questionnaires, architecture reviews, AI/model-risk reviews, and penetration-test remediation.
- Own deployment go-live checklists, sign-off criteria, rollback plans, and partner user acceptance testing.
- Define and enforce partner data access, storage, separation, deletion, and model-training practices.
- Monitor production deployments with dashboards and alerting, and lead safety or security incident response with partners.
- Collaborate with Research, Product, engineering, and security teams to ship secure models and features.
- Create reusable guardrails, tests, and documentation from each deployment.
- Travel for partner launches and security reviews as needed.
Requirements
- 5+ years of experience across security engineering, application security, AI safety, quality engineering, or site reliability.
- Hands-on experience red-teaming LLM applications or agents, including jailbreaks, prompt injection, data exfiltration, and tool or permission abuse.
- Experience designing and tuning LLM product guardrails or safety controls while preserving legitimate customer experiences.
- Experience representing a vendor in enterprise security reviews, architecture reviews, questionnaires, and penetration-test remediation.
- Experience owning production testing and release quality, including automated suites, release gates, load testing, rollback planning, and launch decisions.
- Strong Python skills and the ability to build automated testing harnesses and tooling.
- Experience securing or operating systems for travel or financial-services organizations and understanding fraud, account-takeover, and payment risks.
- Ability to explain risk to engineers, partner security teams, and non-technical executives and push back on unready deployments.
- Preferred experience includes regulated-industry security or risk work, model-risk or AI-governance reviews, OWASP Top 10 for LLM Applications, SOC 2, ISO 27001, PCI DSS, NIST AI RMF, data privacy and governance, Datadog, incident management, multilingual safety testing, voice or conversational AI security, and forward-deployed security engineering.
Benefits
- Remote role, indicated by the #LI-Remote designation.
- Hopper covers 100% of group insurance-plan premiums.
- Life, short-term disability, and long-term disability coverage.
- HSA for eligible medical and dental expenses.
- Dialogue telemedicine access for employees and dependents.
- RRSP plan with automatic pre-tax payroll withdrawals.
- Generous parental leave described as above industry standards.
- Unlimited paid time off.
- Carrot Cash travel stipend.
- On-demand coworking through FlexDesk and a work-from-home stipend.
- Opportunity to work on small, dynamic teams with significant impact.
- Travel may be required for launches and partner reviews.
Tech Stack
DatadogPython
Categories
Forward Deployed
About Hopper
Hopper builds a mobile travel marketplace and a B2B platform (Hopper Technology Solutions) that sells flights, hotels, cars, homes, and travel-fintech products like Price Freeze, Cancel for Any Reason, and disruption assistance to consumers and partner brands. The privately held company is headquartered in Montreal and powers partner‑branded portals such as Capital One Travel and works with airlines like Air Canada and platforms like Uber; its app has surpassed 120 million downloads.
