Machine Learning - Compiler Engineer II, Annapurna Labs

Product

AWS Machine Learning accelerators, including the Inferentia and Trainium chips, enable low‑cost, high‑performance ML inference and training. Together with the AWS Neuron SDK, these tools support Generative AI workloads using popular frameworks such as PyTorch, Tensor Flow, and MXNet.

The Amazon Annapurna Labs team focuses on silicon development across engineering, hardware design, verification, software, and operations. The AWS Neuron subgroup develops a deep learning compiler that converts neural‑network models into efficient code for custom hardware.

As a Machine Learning Compiler Engineer II, you will design and implement core compiler features for large ML workloads, publish research, collaborate with AWS ML service teams, and participate in pre‑silicon design and product‑launch activities.

• 3+ years of non‑internship professional software development experience
• 2+ years of non‑internship system design or architecture experience
• Experience programming with at least one software language
• 2+ years of experience architecting and optimizing compilers
• Proficiency with C++ (preferred), C, or Python

• 3+ years of full software development life cycle experience (coding, reviews, CI/CD, testing, operations)
• Bachelor’s degree in computer science or equivalent; advanced degrees (MS, PhD) considered an asset
• Experience with multiple tool chains and instruction set architectures
• Skills in resource management, scheduling, code generation, and compute‑graph optimization
• Experience optimizing deep‑learning models in Tensor Flow, PyTorch, or MXNet

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Los Angeles County applicants:
Job duties include safely and cooperatively working with other employees, adhering to standards of excellence, communicating respectfully, and following all applicable laws and company policies.

USA, CA, Cupertino – $ – $ USD annually
USA, MA, Boston – $ – $ USD annually
USA, WA, Seattle – $ – $ USD annually