ML Compiler Engineer, AWS Neuron, Annapurna Labs

AWS Neuron team is seeking a ML Compiler Engineer to join Annapurna Labs, the infrastructure provider of AWS. This role focuses on developing compiler technology for AWS Inferentia and Trainium, custom chips designed for deep-learning workloads. The position involves working with the Neuron SDK, which includes a compiler, run-time, and debugger integrated with major ML frameworks.

As a deep learning compiler engineer, you'll be at the intersection of machine learning, high-performance computing, and distributed architectures. The role offers unique opportunities to work on cutting-edge products that impact millions of users worldwide. You'll be involved in pre-silicon design, bringing new products to market, and developing solutions that democratize access to cutting-edge infrastructure.

The team operates in a startup-like environment within AWS, focusing on innovation and experimentation. You'll work with diverse teams across multiple disciplines including silicon engineering, hardware design, software, and operations. The role requires technical expertise and curiosity, as you'll be supporting AWS ML services teams and contributing to various exciting projects.

AWS values diverse experiences and maintains an inclusive culture. The team emphasizes work-life balance and provides flexibility in working hours. Career growth is supported through knowledge sharing, mentorship, and opportunities to work on increasingly complex tasks. You'll be part of a team that has delivered significant products like AWS Nitro, ENA, EFA, Graviton, and ML Accelerators.

This position offers the chance to work on some of the world's largest ML workloads while contributing to innovative solutions that transform how businesses operate. The role combines technical challenge with business impact, making it ideal for engineers passionate about pushing the boundaries of ML infrastructure.