19 Nov
|
EviSmart
|
Winnipeg
Build production AI systems with Python and Kubernetes at EviSmart, working onsite five days weekly from Vancouver. Scale cloud GPU infrastructure reliably.As a Software Engineer, Applied AI, you will turn working models into dependable products running across cloud environments. You will work with Python, PyTorch, Docker, Kubernetes, CI/CD, and machine learning serving frameworks. The work supports EviSmart’s dental industry platform and its in-house AI model team. You will own production uptime, deployment, monitoring, and incident response while coordinating with CAD design and QC teams. This is an individual contributor role with shared on-call responsibility.Key Responsibilities:
Scale AI models on cloud GPU infrastructureBuild packaging, versioning, staged releases, and rollback pipelinesMonitor uptime, speed,
and model performanceRespond to incidents and document corrective changesProvide reproducible training infrastructure and versioned dataRequirements:
Three-plus years running production cloud servicesProduction machine learning deployment experience, ideally using GPUsDocker, Kubernetes, infrastructure as code, and CI/CD experienceMonitoring, alerting, and real production incident experienceStrong Python and comfort reading PyTorch codeBring cloud engineering, machine learning deployment, and operational ownership to EviSmart’s applied AI products in Vancouver.
#J-18808-Ljbffr
📌 Machine Learning Platform Engineer (Winnipeg)
🏢 EviSmart
📍 Winnipeg