22 Nov
|
Vector Institute
|
Winnipeg
22 Nov
Vector Institute
Winnipeg
Build NVIDIA LPX inference optimizations in Toronto or remotely, applying compiler development, systems programming, and deep learning expertise.
As a Senior Machine Learning Applications and Compiler Engineer, you will develop algorithms for NVIDIA’s inference and compiler stack. The work spans large-scale systems, compilers, and deep learning, mapping neural network workloads onto future NVIDIA platforms. You will contribute across runtime components, compiler optimizations, and software integrations.
Key Responsibilities
Build and maintain runtime and compiler componentsDefine mappings for large-scale inference workloadsIntegrate libraries, tooling, and model deployment interfacesBenchmark and profile neural network graph mappingsPrototype graph, scheduling, memory, and layout optimizationsRequirements:
MS or PhD, or equivalent experience, with five relevant yearsSystems programming proficiency in C, C++, and/or RustCompiler or runtime development experienceLLVM and/or MLIR experienceTensorFlow, PyTorch, or ONNX familiarityApply compiler, runtime, and deep learning expertise to optimize NVIDIA LPX inference across future platforms.
#J-18808-Ljbffr
📌 Senior Machine Learning Compiler Engineer (Winnipeg)
🏢 Vector Institute
📍 Winnipeg