MS student intern implementing and optimizing ONNX operator kernels for a GPNPU architecture, leveraging C/C++/Python and performance profiling skills.
Internship focused on model pruning for neural network inference optimization on Quadric's GPNPU architecture. MS student role requiring Python, PyTorch pruning experience, and quantization knowledge.
Develops and optimizes deep learning compiler passes for Quadric's GPNPU, lowering ONNX models through Relay IR to efficient C++ code. Requires new grad-level proficiency in Python, C++, and compiler concepts like IR transformations and debugging.
Develops custom quantization algorithms and prototypes for optimizing ML models on Quadric's GPNPU hardware. Requires MS/PhD, 5+ years in model optimization, deep quantization expertise, and Python/PyTorch proficiency.
AI Inference Engineer ports, optimizes, and benchmarks AI/LLM models on Quadric's GPNPU platform for edge devices. Requires 5+ years in model inference frameworks, quantization expertise, and proficiency in C++/Python.
Develops AI applications and demos using Quadric's SDK, integrates products into AI/LLM frameworks, optimizes models for edge devices, and provides technical leadership and support to customers and developer community. Requires 5+ years with AI frameworks like PyTorch or TensorFlow, plus Python/C++ proficiency.
Develops and optimizes deep neural networks for Quadric's GPNPU architecture, focusing on algorithmic lowering, graph-based execution, and performance extraction. Requires MS/PhD, 8+ years experience in optimization, ML algorithms, and graphs.
MS student intern implementing and optimizing ONNX operator kernels for a GPNPU architecture, leveraging C/C++/Python and performance profiling skills.
Internship focused on model pruning for neural network inference optimization on Quadric's GPNPU architecture. MS student role requiring Python, PyTorch pruning experience, and quantization knowledge.
Develops and optimizes deep learning compiler passes for Quadric's GPNPU, lowering ONNX models through Relay IR to efficient C++ code. Requires new grad-level proficiency in Python, C++, and compiler concepts like IR transformations and debugging.
Develops custom quantization algorithms and prototypes for optimizing ML models on Quadric's GPNPU hardware. Requires MS/PhD, 5+ years in model optimization, deep quantization expertise, and Python/PyTorch proficiency.
AI Inference Engineer ports, optimizes, and benchmarks AI/LLM models on Quadric's GPNPU platform for edge devices. Requires 5+ years in model inference frameworks, quantization expertise, and proficiency in C++/Python.
Develops AI applications and demos using Quadric's SDK, integrates products into AI/LLM frameworks, optimizes models for edge devices, and provides technical leadership and support to customers and developer community. Requires 5+ years with AI frameworks like PyTorch or TensorFlow, plus Python/C++ proficiency.
Develops and optimizes deep neural networks for Quadric's GPNPU architecture, focusing on algorithmic lowering, graph-based execution, and performance extraction. Requires MS/PhD, 8+ years experience in optimization, ML algorithms, and graphs.