We are looking for a talented and passionate software engineer to be part of an exciting technology creation team at Amazon. You will have an enormous opportunity to make a large impact on the design, architecture, and implementation of deep learning technologies embedded into consumer products used every day, by people you know. The position provides an unique opportunity to contribute and make an impact from hardware design stage followed by pre and post silicon development as well as productizing it on consumer devices.

In this role you will be work along side partner science teams to develop the compiler infrastructure and lower deep learning workloads to heterogeneous device backends. You will also partner up with peer science teams to innovate on model quantization and compression techniques for efficient execution on hardware.

Key job responsibilities

Design and develop software stack for deep learning accelerator

Develop Compiler passes for graph ingestions, optimizations and partitioning.

Develop backend code generation capabilities across heterogeneous platforms

Profile, analyze and optimize system level performance, develop new tooling where necessary

Participate in design reviews, API development, and documentation

Successfully collaborate with hardware, software, applied science and product teams to onboard more and more user experiences to be powered by Deep Learning accelerator.

Mentor and provide guidance to junior engineers

A day in the life

You join a small team building the compiler that brings large AI models to a new generation of custom silicon. The chip has a fraction of the memory of a phone, and the compiler is what makes language models run on it at all. The team is small enough that each engineer owns a meaningful piece of the system end to end. There is no layer between you and the problem.

The morning starts with results from an overnight run. A piece of the compiler you own just produced its tightest result yet on a real model. You ship the change for hardware validation.

You spend the afternoon directing AI agents through the codebase, reviewing their changes, and steering the design.

Before lunch, you load your compiled model onto the chip and run it through a demo app you wrote yourself, watching tokens stream out of silicon you helped make work. Later, you meet with the research team. They depend on your component. You sketch a cleaner interface together.

About the team

We sit at the intersection of AI models and custom silicon, and our work decides what is possible at the edge.

Engineers here bring deep experience across compilers and program analysis, optimization algorithms, computer architecture, machine learning systems, and the practical craft of getting large software to run reliably under tight constraints. People have shipped production code generators, tuned schedulers for novel hardware, and worked at every layer from the model down to the bare metal.

Because the team is small, you work alongside that experience daily, not at a distance. You partner directly with researchers shaping the models, hardware engineers shaping the silicon, and firmware engineers shaping the runtime. You learn how each layer constrains and unlocks the others, and you see your decisions land end to end.

This is a place to build technical depth quickly and own work that matters from day one.

BASIC QUALIFICATIONS

- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience

- 3+ years of non-internship professional software development experience

- 3+ years of programming using a modern programming language such as Java, C++, or C#, including object-oriented design experience

- Experience in developing and deploying LLMs in production on GPUs, Neuron, TPU or other AI acceleration hardware

PREFERRED QUALIFICATIONS

- 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience

- Bachelor's degree in computer science or equivalent

- Experience in embedded development in C/C++

- Experience building compiler for application specific accelerators or custom instruction set

The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.

USA, CA, Sunnyvale - 165,200.00 - 223,600.00 USD annually