Machine Learning Systems Engineer

About the company Our client is a software company. The role Raydar is recruiting for this role on behalf of our client. Own low-level performance work for machine learning model serving in production, tuning compute clusters and building the tooling that measures results. Partner with researchers to bring new model designs into live systems, and speak directly with customers when technical needs have to be pinned down. What you'll do - Design, deploy and tune model serving systems across multi-node clusters to raise throughput and cut response times for production workloads. - Implement targeted performance improvements and benchmark their impact. - Diagnose performance bottlenecks across the stack, from GPU execution to memory limits.…