System Development Engineer - EdgeAI, HW Compute Group

Amazon; Bengaluru; On-site; INR 1,900,000 - 2,900,000; Full time

Job summary

Amazon is hiring for an on-device AI SysDE I role focused on the Neural Network Accelerator (NNA) stack. You will work on compiling, deploying, and running vision and language models on in-house accelerators, spanning ML compilation, runtime, and release tooling for millions of devices.

You will collaborate across ML systems, embedded software, and release engineering, contributing to test automation and CI systems for large-scale device fleets.

Qualifications

• Bachelor's degree or above in computer science, computer engineering, or related field.
• Experience working in a Linux/Unix environment.
• Strong programming skills in C, C++, or Python.
• Experience with automating, building, testing, or deploying software.
• Experience with CI/CD pipelines, build systems, and multi-package release engineering.

Responsibilities

• Contribute to the ML compilation pipeline (quantization, graph lowering, kernel selection, artifact packaging).
• Develop on-device inference runtime across secure/non-secure execution paths and manage memory/bandwidth budgets.
• Support release and validation infrastructure to keep device fleets healthy build over build.
• Build and improve test/evaluation systems for model accuracy, latency, and stability on physical devices.

Skills

C

C++

Python

CI/CD

Release engineering

Education

Bachelor's degree or above in CS/CE or related field

Tools

Linux/Unix

ADB

Job description

Are you passionate about running large AI models directly on consumer devices — where every millisecond, milliwatt, and megabyte matters? Join our team to work at the core of the Neural Network Accelerator (NNA) software stack, driving on-device machine-learning inference, compiler and runtime development, and the automation infrastructure that ships production-quality AI features to millions of Amazon devices.

Key job responsibilities

As a SysDE I on the NNA / EdgeAI team, you will contribute to the software stack that compiles, deploys, and runs vision and language models on Amazon's in-house neural accelerators. You will work across the ML compilation pipeline (quantization, graph lowering, kernel selection, artifact packaging), the on-device inference runtime (secure and non-secure execution paths, memory and bandwidth budgets), and the release and validation infrastructure that keeps our device fleet healthy build over build.

A day in the life

You will help build and improve the test and evaluation systems that validate model accuracy, latency, memory footprint, and stability on physical devices in the lab — including large-scale evaluation of Vision-Language Models (VLMs) end-to-end from reference to device. You will also contribute to the build, release, and CI automation that keeps our multi-package software stack shipping cleanly across product platforms.

This role sits at the intersection of ML systems, embedded software, and release engineering.

Basic Qualifications

• Bachelor's degree or above in computer science, computer engineering, or related field
• Experience working in a Linux/Unix environment
• Strong programming skills in one or more of C, C++, Python
• Experience with automating, building, testing, or deploying software
• Experience with CI/CD pipelines, build systems, and multi-package release engineering

Preferred Qualifications

• Familiarity with machine learning fundamentals — model formats, quantization, inference vs training
• Experience with on-device or embedded ML runtimes, ML compilers, or accelerator toolchains
• Experience with device-side debugging: kernel logs, driver logs, ADB, on-device tracing
• Familiarity with cloud infrastructure (AWS) for large-scale test execution, log storage, and metrics
• Familiarity with agent-based / AI-assisted developer tooling for triage, code review, or release automation
• Minimum 3 year of experience in ML systems, embedded software, or release engineering

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.

Company

- ADCI - BLR 14 SEZ

Job ID: A10573481