About the job
This role is for a Senior Machine Learning Engineer in the Distribute Training team for AWS Neuron, responsible for development, enablement and performance tuning of a wide variety of ML model families, including massive-scale Large Language Models (LLM) such as GPT and Llama, as well as Stable Diffusion, Vision Transformers (ViT) and many more. The ML Distributed Training team works side by side with chip architects, compiler engineers and runtime engineers to create, build and tune distributed training solutions with Trainium instances.
Responsibilities
You will lead efforts to build distributed training support into PyTorch and JAX using XLA, the Neuron compiler, and runtime stacks. You will optimize models to achieve peak performance and maximize efficiency on AWS custom silicon, including Trainium and Inferentia, as well as Trn2, Trn1, Inf1, and Inf2 servers.
Qualifications
Minimum
Experience with training these large models using Python is a must. Strong software development skills, the ability to deep dive, work effectively within cross-functional teams, and a solid foundation in Machine Learning are critical for success in this role.
Preferred
Experience with training these large models using Python is a must. FSDP (Fully-Sharded Data Parallel), Deepspeed, Nemo and other distributed training libraries are central to this and extending all of this for the Neuron based system is key. Strong software development skills, the ability to deep dive, work effectively within cross-functional teams, and a solid foundation in Machine Learning are critical for success in this role.