Architect system-level test suites that stress control-plane and data-plane components beyond provisioning and vetting flows.
Build and maintain performance benchmarking infrastructure for LLM inference workloads (Prefill + Decode), including dashboarding and regression detection.
Drive integration of third-party vendor code (nightly drops) into CI/CD, ensuring quality gates catch regressions early.
Participate in feature design reviews, contributing test plans and challenging coverage gaps.
Define and own Continuous Testing in production environments (CTS).
Leverage AI-assisted development tools (Kiro, LLM-based code generation) to accelerate team velocity and pioneer new engineering workflows.
A day in the life
You'll start your day reviewing CI pipeline results from overnight runs, triaging failures to determine whether a regression came from a vendor code drop, a firmware change, or an ML serving stack update. Mid-morning you might pair with a hardware engineer to design test cases for a new bus-level reset flow, then pivot to extending the performance benchmarking framework to catch a latency regression. After lunch you'll join a feature design review — challenging test coverage gaps and deciding where system-level validation needs to live. The rest of your afternoon could be spent writing a new pipeline stage that gates deployment on accuracy checks, or building a dashboard that gives the group visibility into fleet-readiness metrics. Throughout the day you'll lean on AI-assisted development tools to accelerate everything from infrastructure code to root-cause analysis.
Experience leading the architecture and design (architecture, design patterns, reliability and scaling) of new and current systems
Experience programming with at least one modern language such as Java, C++, or C# including object-oriented design
7+ 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
Knowledge of Python and/or C++ programming
Experience in developing and deploying LLMs in production on GPUs, Neuron, TPU or other AI acceleration hardware
Experience in DevOps, CI/CD, pipeline, jenkins or other equivalents
Experience with elastic, grafana, cloudwatch, or other equivalents
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.
