About the role
The Inference ML team develops advanced algorithms and model architectures for efficient AI inference on Cerebras hardware. The ML Research Scientist invents, prototypes, and validates new methods, focusing on techniques like speculative decoding and model compression to achieve low-latency, high-throughput inference.
Our summary of the posting; the original is on the Cerebras Systems careers page.
What the posting requires
- Required
- Model performance
- Novel methods
- Model quality
- Python
- PyTorch
- Algorithm performance
- Inference efficiency
- Transformers
- Inference workloads
- Preferred
- Speculative decoding
- Model architectures
- Performance optimization
- Triton
- Pruning
- Specialized hardware
These tags are our reading of the posting. They can miss something; the original posting is the reference.