AMD

Edge & Enterprise System Solution Architect.

AMD
Apply
23 hours ago
Markham, CanadaMid Level

Responsibilities

  • Define end-to-end dGPU, SoC, server, edge, and client platform architectures, including power, thermal, signal integrity, form factor, memory, and interconnect trade-offs.
  • Define hardware telemetry, power monitoring, diagnostics, and integration with enterprise manageability platforms such as iDRAC, iLO, and IPMI.
  • Translate system architecture into requirements for firmware, drivers, runtimes, ROCm libraries, tools, and application stacks.
  • Develop software architecture plans integrating Kubernetes, AI frameworks, and enterprise management tools.
  • Create reference architectures, sizing guidance, and tuning guides; support customer application porting and migration and serve as an escalation point for live software-stack failures.
  • Lead hardware/software interface definition, pre-silicon modeling, post-silicon bring-up, diagnostics, emulation, and silicon validation workflows.
  • Collaborate with SoC architecture, design verification, hardware, driver, performance library, and product management teams.
  • Document reusable architecture patterns, bring-up playbooks, and hardware/software design practices, including standards for AI-assisted development traceability and validation.

Requirements

  • At least 3 years of engineering experience in dGPU/SoC platform architecture, hardware engineering, systems software, firmware, or low-level driver development used to bring new silicon to market.
  • Demonstrated hardware/software co-design experience, including interface definition, performance analysis, and debugging complex hardware, firmware, and software issues.
  • Knowledge of IPMI, iDRAC, iLO, system telemetry frameworks, Prometheus, Grafana, and OpenTelemetry.
  • Hands-on experience deploying and orchestrating containerized GPUs on Linux and Windows using Docker, Podman, and Kubernetes, including K3s for edge nodes.
  • Experience with Slurm or another cluster scheduler for batch and HPC environments.
  • Strong written and verbal communication skills and willingness to travel domestically and internationally occasionally.
  • Knowledge of ML/AI workloads and architectures such as Transformers, Stable Diffusion, CNNs, and UNet, with GPU optimization experience using ROCm or CUDA is desired.
  • Experience with DirectX 12, Vulkan, ray tracing, neural rendering, game-engine profiling, pre-silicon simulation or emulation, server board design, or power integrity analysis is desired.
  • Production AI deployment experience with serving stacks such as vLLM or SGLang is desired.
  • An advanced degree such as an M.Sc., M.Eng., or Ph.D. in Electrical Engineering, Computer Engineering, Computer Science, or a related field is optional.

Tech Stack

DockerGrafanaKubernetesLinuxPrometheusWindows

Categories

Solutions Engineering
AMD

About AMD

10,000+ employees

AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.

Contact me