22 Nov
|
Jobgether
|
Canada
Secure AI agents in production as a Forward Deployed Engineer focused on guardrails and adversarial testing. This position is fully remote within Canada.
You will make agents secure, secure, and production-ready for major banks, airlines, and travel companies. The role combines AI safety, application security, Python tooling, and partner-facing reviews. You will connect partner security, risk, and IT teams with internal engineering and security teams. Your work covers launch readiness, data protection, and live reliability.
Key Responsibilities:
- Tailor guardrails to partner policies, regulations, languages, and risk appetite
- Red-team agents for jailbreaks, injection, leakage, and unauthorized actions
- Build continuous multilingual adversarial and regression test suites
- Lead security reviews, questionnaires,
and penetration-test remediation
- Monitor deployments and lead safety or security incident response
Requirements:
- Five or more years in security, AI safety, quality, or site reliability
- Hands-on LLM red-teaming and guardrail design experience
- Strong Python skills for automated testing and tooling
- Enterprise security review and production release ownership experience
- Willingness to travel for launches and reviews
Apply Forward Deployed Engineer expertise across AI safety, Python automation, partner security, and production reliability.
#J-18808-Ljbffr
📌 Forward Deployed AI Security Engineer (Canada)
🏢 Jobgether
📍 Canada