Senior / Staff Research Engineer, Generative AI Deployment
Toronto, ONHybridFull Time
Waabi
Candidates need experience shipping production ML software and optimizing models for deployment, such as with TensorRT, torch.compile, ONNX or quantization. They also need GPU profiling skills, understanding of modern architectures like diffusion and vision transformers, and experience running GPU jobs in the cloud.
TensorRT, torch.compile, ONNX, CUDA, Triton, Nsight Systems