PnP Optimization Engineer
Remote US & CanadaFull-TimeMid-levelSoftware Engineering
You will…
- - Collaborating with research scientists during algorithm design to ensure code is efficiently designed from inception
- - Identify and communicate best practices for model development
- - Reformulate performance bottlenecks
- - Develop a framework suitable for mixed precision training of multi-task, multi-modality models in a heterogeneous distributed training environment
- - Research, implement, and test alternative formulations for fundamental DNN operations and AV centric representations
- - Enable safe and efficient deployment of PnP models
Qualifications
- - PyTorch API and implementation
- - CUDA system design
- - Asynchronous programming model
- - Heterogeneous compute
- - C++ / libtorch
Bonus
- - Machine learning model architecture design
- - TensorRT
- - CUDA kernel implementation
- - Experience with autonomous vehicle multi-sensor model architectures
