Software Engineer II - AI/ML, AWS Neuron - Amazon

Key Responsibilities

• Design, develop, and maintain high‑performance components of the AWS Neuron SDK, including the ML compiler, runtime, and application framework.
• Collaborate with cross‑functional teams to integrate new features and performance improvements for Inferentia and Trainium accelerators.
• Optimize code for low‑latency inference and high‑throughput training, ensuring scalability across large model deployments.
• Debug, profile, and troubleshoot complex issues in distributed environments, providing actionable insights to improve reliability.
• Contribute to open‑source tooling and internal libraries, documenting best practices and performance guidelines.

Requirements

• Strong experience in C++ and Python for performance‑critical systems.
• Deep knowledge of machine learning frameworks (e.g., TensorFlow, PyTorch) and model optimization techniques.
• Hands‑on experience with AWS services and custom ML accelerators such as Inferentia and Trainium.
• Proficiency in profiling, debugging, and performance tuning of large‑scale ML workloads.
• Excellent communication skills and a collaborative mindset for working in a fast‑paced, distributed team.