NNP Engineer

San Jose, CA - USA

Monthly Salary: Not Disclosed

Posted on: 2 days ago

Vacancies: 1 Vacancy

Job Summary

NNP Engineer
Required Skills - C Compilers SDK Native APIs Python AI/ML PyTorch TensorFlow

Developing techniques such as quantization pruning and model distillation to adapt large neural networks for high-speed execution on specific hardware targets.
Designing and maintaining compilers SDKs and native APIs that act as the interface between deep learning frameworks (like PyTorch) and the underlying NNP hardware
Writing high-performance C kernels for fundamental neural network operations like convolutions and transformers specifically tailored to custom hardware architectures
Using specialized tools to analyze latency memory bandwidth and power consumption then debugging bottlenecks in the software stack.
Building the production-ready pipelines that deploy models onto edge devices or cloud-based AI servers

2 to 7 years of experience

Expert proficiency in Python (for ML frameworks) and modern C (for low-level system software and kernel development).
Deep working knowledge of PyTorch or TensorFlow specifically their backend internals and plugin architectures
Understanding of computer architecture memory management and parallel computing principles (e.g. SIMD multi-core compute)
Familiarity with cross-platform model formats like ONNX and compiler infrastructures like MLIR or LLVM
B.E/ in Electronics & Communication or Computer Science Engineering

NNP Engineer Required Skills - C Compilers SDK Native APIs Python AI/ML PyTorch TensorFlow Developing techniques such as quantization pruning and model distillation to adapt large neural networks for high-speed execution on specific hardware targets. Designing and maintaining compilers SDKs and...