Deploy, configure, and maintain on-prem GPU servers and containerized services for real-time video analytics. Manage deployments, monitoring, automation, and incident debugging; collaborate with ML/backend teams and casino IT to ensure secure, reliable production systems.

Deploy, maintain, and debug real-time computer vision and ML pipelines on-prem at client sites. Train and tune deep learning and classical ML models, optimize low-latency inference with PyTorch/ONNX/TensorRT/Triton, build data/labeling pipelines, and collaborate with customers and partners.