About the role#
As an intern on the Toronto Neuron team within Annapurna Labs, you will work on the software that powers custom silicon, including AWS Trainium accelerators. You will join either the Frontier Model Performance team or the Developer Experience team. You will solve engineering problems with mentorship from experienced machine learning and systems engineers.
What you'll do#
- Bring up and optimize machine learning models for peak performance on AWS Trainium.
- Write and tune kernels, optimize model execution, and build benchmark infrastructure.
- Turn concepts into reusable Neuron components and optimization techniques.
- Build profiling, debugging, and analysis tools for the Neuron Explorer.
- Develop performance data collection engines, interactive visualizations, and developer workflows.
What you'll need#
- Current enrollment in a Bachelor's degree program or higher in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
- Programming experience in Python, C, or C++ through coursework, research, or internships.
- Academic or project experience in at least two of the following: performance engineering, kernel development, developer tooling, data structures, machine learning frameworks like PyTorch or JAX, or compiler technologies like LLVM, MLIR, XLA, or TVM.
- Experience with model optimization, kernel writing for accelerators, or building developer tools is preferred.
- Experience with full stack development (TypeScript, React, Go) or agentic workflows for automation is a plus.
- Ability to explain technical challenges clearly and work through ambiguous problems.
Location & details#
- Location: Toronto, Ontario, Canada.
- Work Modality: On-site.
- Employment: Full-time, paid internship.
- Terms: Winter 2027, Summer 2027, or Fall 2027.
About Amazon
Amazon operates as a public company focused on e-commerce, retail, operations, and internet services. It maintains its headquarters in Seattle, Washington. The organization employs 783,642 people across its various divisions. It functions as a large-scale provider of digital and physical goods.
How to get in at Amazon
Securing an internship at Amazon requires speed because early applicants often reach recruiters before the candidate pile grows too large. Intern Insider sends an instant alert the moment a role matching your target is published, which helps you apply among the first. Applying early is a practical way to ensure your profile is seen by the team. You can also use Intern Insider to surface the recruiters behind specific Amazon roles to reach out directly. Asking about a role or a referral often improves response rates compared to submitting an application into a general queue. Connecting with a human recruiter shows you have done your research and are serious about the opportunity.
