Description
Job Description
Hopper powers travel for some of the world's largest banks, airlines and travel companies, and our AI agents act on their customers' behalf by looking up accounts, changing and cancelling bookings, and handling payments and loyalty points.
As the Forward Deployed Engineer, AI Trust and Reliability, you make sure that AI is safe, secure and ready for production in every partner deployment. You work in a small forward-deployed team as the person who owns guardrails, adversarial testing, launch readiness and partner security reviews, and you are the bridge between our partners' security, risk and IT teams and Hopper's engineering and security teams.
What Would Your Day-to-Day Look Like
- Tailor guardrails to each partner's policies, regulations, risk appetite and languages, covering 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 so they 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
- Turn findings into fixes with engineering, and into regression tests so they stay fixed
- Lead partner security questionnaires, architecture reviews and AI or model-risk reviews, and respond to partner penetration-test findings
- Document how our 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 our 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 our 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 make sure it is followed
- Monitor live deployments for quality, reliability, abuse and safety failures, and set up dashboards and alerting with engineering
- Lead the response when a safety or security issue occurs, with clear communication to the partner throughout
- Work closely with Research, Product and our security team, so new models and features ship with security built in
- Turn each deployment into reusable guardrails, tests and documentation, so the next partner goes faster
Ideal Candidate
- 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, and used the findings to close real gaps
- Designed and tuned guardrails or safety controls for an LLM-based product, and can show where they stopped real risk without hurting the customer experience
- Represented a vendor in enterprise security reviews, including questionnaires, architecture reviews and penetration-test remediation, and brought partner security teams to sign-off
- Owned testing, quality and validation of production system versions, automated test suites and validation criteria up to load testing and rollback, and delayed launches because the system wasn't ready
- Proficient in Python and creating automated tools and test banks that enable continuous adversarial and regression testing
- Experience securing or exploiting systems for travel or financial services companies like airlines, hotels, online travel agencies, banks or payment companies, and understands the risks of fraud, account takeover and payment unique to them
- Can clearly explain risks to engineers, partner security teams and non-technical executives, and isn't afraid to push back when a deployment isn't ready
- Willing to travel for launches and reviews
- Asset: work in security or risk management in regulated sectors like banking, payments or aviation, or AI governance and model risk reviews in a financial institution
- Asset: knowledge of AI-related security and risk frameworks like OWASP Top 10 for LLM Applications, SOC 2, ISO 27001, PCI DSS and NIST AI RMF
- Asset: experience in data protection and governance, like data-sharing agreements, secure access to client systems or GDPR and similar regimes (e.g., Law 25 in Quebec)
- Asset: experience in observability and incident management, e.g., with Datadog, post-incident analysis
- Asset: multilingual security testing or conversational AI security
- Asset: experience in deployed security engineering or direct customer engagement
Benefits
- A well-funded startup with big ambitions, competitive salary and pre-IPO equity benefits
- Hopper covers 100% of group insurance premiums
- Hopper offers life, short-term disability and long-term disability coverage
- Health spending account covering eligible medical and dental expenses
- All employees and dependents have access to Dialogue telemedicine services 24/7, anywhere
- All employees have access to a RRSP plan with automatic pre-tax deductions from each pay cheque
- Learn about our generous parental leave policy, far exceeding industry standards
- Unlimited vacation days
- Carrot Cash travel allowance
- Access to on-demand coworking space via FlexDesk and a remote work allowance
- Entrepreneurial culture where pushing limits and taking risks is part of the daily routine
- Open communication with management and company leaders
- Small, dynamic teams and significant impact
For more fresh new jobs, check out yubhub.co.