Contribute to the development of the world's first AI inference system for transformers, focusing on
岗位职责
As an Inference Intern at Etched, you will contribute to the development and optimization of our AI inference system designed for transformer models. Your responsibilities will include:
Model Optimization: Work on optimizing transformer-based models for inference on custom ASIC hardware, focusing on reducing latency and improving throughput.
Benchmarking and Testing: Design and execute benchmarks to evaluate the performance of inference systems, comparing against GPU-based solutions like B200.
申请条件
To succeed in this role, you should have:
Currently pursuing a Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field.
Strong programming skills in Python and C++.
Familiarity with deep learning frameworks such as PyTorch or TensorFlow.
雇主简介
Etched is building the world's first AI inference system purpose-built for transformers, delivering over 10x higher performance and lower cost than GPUs.