Software Development Manager - NKI Compiler, AWS Neuron, Annapurna Labs

The Product: AWS Machine Learning accelerators are at the forefront of AWS innovation. Trainium delivers best-in-class ML training performance with the most teraflops (TFLOPS) of compute power for ML in the cloud. This is all enabled by the AWS Neuron Software Development Kit (SDK), which includes an ML compiler, the Neuron Kernel Interface (NKI) compiler, and a runtime that natively integrates into popular ML frameworks such as PyTorch and JAX.

Neuron Kernel Interface (NKI) is a bare-metal language and compiler for directly programming Neuron Devices available on AWS Trainium instances. You can use NKI to develop, optimize, and run new operators directly on Neuron Cores while making full use of available compute and memory resources.

Explore NKI:
- https://awsdocs
- AWS Neuron is used at scale by customers such as Epic Games, Snap, Airbnb, Autodesk, Amazon Alexa, and Amazon Rekognition, along with many others across a range of segments.

The Team:
The Amazon Annapurna Labs team is responsible for building innovative silicon and software for AWS customers. We are at the forefront of innovation, combining cloud scale with the world's most talented engineers. Our team covers multiple disciplines including silicon engineering, hardware design and verification, software, and operations. With such breadth of talent, there is opportunity to learn all of the time.

We operate in spaces that are very large, yet our teams remain small and agile. There is no blueprint. We're inventing. We're experimenting. When you couple that with the ability to work on so many different products and services, it makes for a unique learning culture.

Learn more about our history: https://(Use the "Apply for this Job" box below).-success

You:
We are seeking a talented Software Development Manager with strong leadership and mentoring skills to join our NKI development team. As an SDM III, you will lead a team of experienced compiler engineers developing compiler optimization algorithms and deploying, at scale, a new compiler targeting AWS custom hardware. You will need to be technically capable, credible, and curious in your own right as a trusted AWS Neuron manager, innovating on behalf of our customers.

You will draw on knowledge of resource management, scheduling, code generation, optimization, and instruction architectures across CPU, NPU, GPU, and novel forms of compute. You will leverage your technical communication skills to partner with AWS ML services teams and pre-silicon design, and to bring new products and features to market. As deep learning models become more versatile, using compiler technologies to achieve both high performance and high productivity becomes essential.

Join the team to build the software that boosts the entire deep learning community.

Explore the Product:

- - https://awsdocs
- In order to be considered for this role, candidates must be currently located in or willing to relocate to Cupertino, CA.

Key job responsibilities
- Lead, grow, and mentor a team of compiler engineers, including hiring, career development, and team health
- Own execution and delivery of NKI compiler features across release cycles, balancing scope, quality, and timelines
- Set technical direction and roadmap for your area of the NKI compiler in partnership with senior engineers
- Partner across teams, including frameworks, kernel development, runtime, hardware/pre-silicon design, and product management, to bring new features to market
- Drive resolution of complex, high-priority technical issues, staying close enough to the code and hardware to guide the team
- Represent your team's work and priorities to senior leadership and cross-organizational stakeholders
- Anchor decisions in customer impact, ensuring the team builds what unblocks real ML workloads on Trainium

A day in the life
No two days look the same on the NKI team, but most blend people leadership, technical depth, and cross-team collaboration.

You might start the morning in a 1:1 with an engineer, working through the design of a new compiler optimization or unblocking a tricky scheduling problem. Mid-morning, you join a release sync to…