Principal ML Engineer: Large-Scale Training & Performance

AMD; San Jose (CA); Hybrid; USD 130,000 - 160,000; Full time

Benefits offered by this job

Comprehensive benefits package

Flexible work arrangements

Collaborative work environment

Job summary

A leading tech company is seeking a Principal Machine Learning Engineer in San Jose, CA. This role involves training large models on AMD GPUs and optimizing the training pipeline for efficiency. The ideal candidate should have extensive experience with distributed training algorithms and ML/DL frameworks like PyTorch and TensorFlow. The position offers the opportunity to work in a collaborative and innovative environment focused on AI advancements.

Qualifications

• Experience with distributed training algorithms (Data Parallel, Tensor Parallel, etc.)
• Familiarity with training large models at scale.
• Experience optimizing GPU kernel performance.

Responsibilities

• Train large models to convergence on AMD GPUs.
• Improve the training pipeline performance.
• Optimize distributed training pipeline and algorithm.
• Contribute changes to open source.
• Influence direction of AMD AI platform.

Skills

Distributed training pipelines

ML/DL frameworks (PyTorch, JAX, TensorFlow)

Communication skills

Problem-solving skills

Python or C++ programming

Education

Master's or PhD in Computer Science, AI, or ML

Tools

Megatron-LM

MaxText

TorchTitan

Job description

A leading tech company is seeking a Principal Machine Learning Engineer in San Jose, CA. This role involves training large models on AMD GPUs and optimizing the training pipeline for efficiency. The ideal candidate should have extensive experience with distributed training algorithms and ML/DL frameworks like PyTorch and TensorFlow. The position offers the opportunity to work in a collaborative and innovative environment focused on AI advancements.