Overview
Role focused on productionising and scaling generative models in a high-throughput environment.
Ideal candidate has proven experience deploying diffusion-based models and optimising inference across GPUs.
remoteseniorpermanentfull-timeEnglishPythonPyTorch
Locations
Canada, British Columbia, Vancouver
Requirements
Experience with deploying generative models Proficiency in Python and PyTorch Familiarity with MLOps practices
Responsibilities
Build and maintain production pipelines Contribute to high-throughput GenAI systems Utilise optimisations for speed and efficiency Collaborate with researchers on model innovation Tackle end-to-end challenges
Benefits
Annual wellbeing allowance Professional development support