AI Platform Engineer - EZRA

Ezra

45d•Remote

About The Position

As an AI Platform Engineer (LLMOps), you will build and operate the production AI platform that powers EZRA’s AI-first features. Reporting to the VP of Engineering, you will ensure AI systems are scalable, observable, secure, and reliable, enabling teams to safely deploy and iterate on AI capabilities in production.

Requirements

6+ years of experience in platform engineering, DevOps/SRE, or backend operations for production systems
Hands-on experience building CI/CD pipelines and managing cloud infrastructure in production environments
Strong understanding of observability practices (metrics, logging, distributed tracing) and incident management workflows
Familiarity with operational considerations for AI/LLM systems (latency, rate limits, token usage, cost drivers)
Experience managing infrastructure or configuration changes through code review and controlled release processes
Experience optimizing system reliability, performance, and cost in a production environment

Responsibilities

Design, build, and operate the AI runtime platform, including deployment pipelines, environment configuration, and scaling strategies
Implement observability and monitoring across AI systems, with dashboards, alerting, and incident response processes
Manage prompt and model configuration lifecycle, including versioning, approvals, routing logic, and rollback mechanisms
Ensure security and compliance standards are met through access controls, auditability, and safe data handling practices
Optimize AI system performance and cost through usage monitoring, caching strategies, and capacity planning