AI/ML Infrastructure Engineer

📋 Description

• Optimizing Core ML Pipelines for video analytics.
• Cross-Stack Collaboration with AI research and platform teams.
• Model acceleration with quantization, pruning, and layer fusion.
• Build efficient operators across PyTorch, CUDA, TensorRT, and DeepStream.
• Improve resource efficiency to reduce compute cost per video stream.
• Data management for visual data collection and labeling.

🎯 Requirements

• BS/MS or PhD in CS, EE, or related field.
• Strong programming in C/C++ and Python.
• Experience with model optimization, quantization, and pruning.
• Deep understanding of GPU performance and memory hierarchy.
• Experience with profiling/benchmarking tools (Nsight Systems, Nsight Compute).
• Experience resolving compute and data-flow bottlenecks.