Matterport - Senior ML Ops Engineer

Senior ML Ops Engineer at Matterport/CoStar Group responsible for enhancing model performance, efficiency, and scalability. Analyze and profile ML models to identify bottlenecks; implement optimization techniques (quantization, pruning, distillation, neural architecture search); develop and integrate libraries/tools for efficient model execution on GPUs/CPUs/edge devices; collaborate with ML R&D to understand architectures and deployment requirements; design experiments to measure impact of optimizations on performance and accuracy; automate ML optimization workflows and CI/CD pipelines for production models; stay up-to-date with ML model optimization and hardware acceleration trends; ensure scalability and reliability of optimized models in production; role based in Sunnyvale, CA with a 4-days-on-site/1-day-work-from-home arrangement.