Optimize machine learning inference with GPU performance tuning while working remotely from Canada or the UK in a full time position. Build dependable serving systems for high request volumes.Raydar recruits for its software company client, seeking a senior engineer to move trained models from research into production. The work combines server-side software, inference optimization frameworks, systems programming, and distributed serving. You will improve model performance and operate services across GPUs and nodes.Key Responsibilities: Optimize model serving latency and throughputContainerize models for reliable production deploymentProfile and tune GPU-based codeDesign distributed serving across GPUs and nodesApply quantization, batching, and caching methodsRequirements: Senior-level software or inference engineering experienceProduction experience with server-side or learning-based softwareMachine learning inference optimization framework experienceC++, CUDA, Rust, or optimized Python proficiencyDistributed systems and container orchestration familiarityUse inference optimization, GPU programming, and distributed systems expertise to deliver reliable machine learning production serving.#J-18808-Ljbffr