Edge AI Platform Engineer

Job Description

Build the platform that runs SEVN — the software infrastructure that deploys, monitors, and scales vision models across the fleet of edge nodes on the line.

What you'll do

Build and operate the platform that provisions, deploys, and updates vision models across every station's edge node.

Own fleet management — device health, model versioning, safe rollouts, and over-the-air updates.

Build the data platform: pipelines from cameras and machines to storage, turning frames into traceable defect records.

Instrument observability — latency, accuracy, uptime, and drift monitoring across the network.

Containerize and orchestrate edge workloads for 24/7 reliability at scale.

Partner with CV/ML, controls, and quality to integrate inference into daily operations.

What you bring

BS / MS in Computer Science, EE, or related — or equivalent experience.

3+ years in platform, ML infrastructure, or backend / distributed systems.

Experience with containers and orchestration (Docker, Kubernetes, or edge device management).

Strong Python (and/or Go); data pipelines and cloud / edge deployment.

Familiarity with edge hardware (e.g. NVIDIA Jetson) and real-time systems a plus.

Full-time