Cayla Schuval

Background

About Cayla Schuval

Machine Learning Engineer with experience building and scaling infrastructure to support real-time, production-grade ML systems. I specialize in MLOps, with a focus on model deployment, orchestration, observability, and performance optimization. My recent work includes designing distributed inference systems, automating CI/CD pipelines, improving platform reliability during peak traffic events, and driving on-call and incident response readiness. I’ve worked extensively with Kubernetes, Ray, Terraform, Jenkins, Argo Workflows, and AWS to deliver resilient, scalable systems that support low-latency model serving at scale. I’m especially passionate about solving platform-level challenges in ML — from infrastructure to monitoring — and enabling teams to move faster, more safely, and with confidence in production.