About the role
The Inference Research team builds scalable systems for serving large AI models. The intern explores distributed inference, compiler improvements, and novel computational methods. They will design and implement cross-layer enhancements for models, systems, and hardware, concentrating on KV cache and large-scale deployment.
Our summary of the posting; the original is on the Together AI careers page.
What the posting requires
- Required
- PyTorch
- Python
- JAX
- Programming
- Deep learning frameworks
- Machine Learning
- Transformer architectures
- Deep Learning
- Foundation models
- Bachelor
- Preferred
- CUDA programming
- Kernel development
- Model optimization
- Hardware acceleration
- Research
- Publications
These tags are our reading of the posting. They can miss something; the original posting is the reference.