Summary
✨ AI‑Generated
A staff engineering role responsible for bringing autonomous AI systems into production through deployment automation, security controls, testing, monitoring, and reliability practices.
Highlights
Remote staff-level role focused on deploying, securing, and operating advanced AI agent systems in production.
Description
Staff Engineer I Agentic AI Platform Deployment Engineer
Remote
Position Summary
The Agentic Platform Deployment Engineer takes autonomous AI agents (systems that plan and execute complex, multi-step tasks across enterprise software) from validated design into safe, observable production operation, using platforms such as Claude, Copilot, Edifecs Agent Platform, or Google's agentic platform.
This role focuses on agent deployment, testing, and launch.
Key Responsibilities
Own the deployment pipeline: staging, canary rollout, and production cutoverDefine least-privileged permission and tool access boundaries for autonomous agentsRun pre-launch adversarial testing (prompt injection, tool misuse, unsafe plans) before production exposureImplement human-in-the-loop approval gates and escalation paths for high-risk agent actionsBuild observability, audit logging, and kill switch/rollback mechanisms for agent behaviorLead incident response for agent failures and track task success, cost, and latency in productionPartner with architects, AI engineering, and security on rollout strategy; mentor engineers on safe deployment
Required Qualifications
Bachelor's degree in computer science or equivalent.8 to 10+ years enterprise software engineering experience, with ownership of production deployment/operationsHands-on experience deploying or operating agentic AI systems (Claude, Copilot, Edifecs, or Google's agentic platform)Strong grasp of AI safety and guardrail patterns: sandboxing, permission scoping, rollback designPractical CI/CD, DevSecOps, and cloud deployment experience (OpenShift, Kubernetes, AWS).
Preferred Qualifications
Direct experience with Edifecs Agent Platform or Google's agentic platform in productionExperience running red team or adversarial evaluations against LLM agentsExperience defining SLOs and alerting for agent reliability
