Remotely
pytorchcudatritongpudiffusionautoregressive
Job Description
📋 Description
- Build and scale video generation models in a production setting
- Improve training and inference efficiency (memory, latency, cost)
- Explore distillation, quantization, pruning to speed up diffusion and autoregressive models
- Develop distributed training systems and optimize GPU utilization
- Translate research into robust production tooling and systems
- Monitor model performance in real-world usage
🎯 Requirements
- BS/MS/PhD in CS, ML, or related field
- 2+ years of professional industry experience
- Strong experience in deep learning systems and infrastructure
- Expertise in PyTorch, CUDA, Triton, and distributed training (FSDP, etc.)
- Experience scaling large models with low-latency inference
- Strong debugging and performance profiling skills
🎁 Benefits
- Comprehensive medical, dental, and vision plans
- 401K with employer match
- Commuter Benefits
- Catered lunch multiple days per week
- Dinner stipend if working late
- Grubhub subscription
Back to all jobs
