Systems Development Engineer, Edge AI Platform Infrastructure, Hardware Compute Group
Core
Design and maintain automated hardware-in-the-loop test infrastructure and CI/CD pipelines to validate custom AI accelerator silicon IP, kernel drivers, and ML inference software across Amazon's edge device portfolio.
Role type
Systems Development Engineer (Edge AI Platform Infrastructure)
Builds
Automated test frameworks, CI/CD pipelines, and production monitoring dashboards for AI accelerator silicon.
Domain
Hardware compute, embedded systems, AI accelerator validation, cloud infrastructure.
Deliverable
production ML models | infrastructure
Required skills
Python, C/C++, hardware-in-the-loop test automation, CI/CD pipeline design, hardware IP concepts (registers, DMA, interrupts, memory-mapped I/O), code coverage tooling, static/dynamic analysis integration.
Preferred skills
AI/ML tools for engineering productivity, embedded Linux build systems (Yocto/OpenEmbedded), neural network accelerator architectures, AWS infrastructure services, hardware security concepts (IOMMU, secure boot, ARM TrustZone), SCA/DCA tools, ML inference runtimes.
Technologies
Python, C, C++, AWS (CDK, Lambda, CodePipeline, CloudWatch, S3, Step Functions), Yocto, BitBake, Jenkins, Coverity, CodeQL, Klocwork, ASAN, TSAN, Valgrind.
Responsibilities
Design and maintain automated test systems executing on physical AI accelerator silicon; develop deep understanding of AI accelerator hardware IP to write meaningful validation; define and implement new test methodologies and frameworks; apply AI fundamentals to automate log analysis, test selection, and failure pattern recognition; implement code coverage, static analysis, and dynamic analysis integrated into CI workflows; build and maintain release pipelines using AWS services and embedded build systems; create dashboards and alerting for on-device inference metrics and performance regressions.
Seniority
Mid-level, hands-on IC
