Principal Systems Design Engineer.

Advanced Micro Devices, Inc•Austin, TX

About The Position

The Edge & Enterprise Solution Architect is the core technical authority for defining, architecting, and deploying end-to-end GPU-accelerated computing solutions for enterprise data centers, hybrid cloud environments, and edge platforms. The role bridges customer workload requirements and system architecture, combining GPU hardware platforms with software application stacks to address enterprise and edge challenges. The position partners with enterprise customers, ISVs, systems integrators, and internal hardware, firmware, driver, and software teams to translate business needs into scalable and secure deployment blueprints. Its scope spans GPU compute hardware, thermals, form factors, high-speed interconnects, enterprise management interfaces, AI/ML frameworks, edge orchestration, telemetry, security, and application stacks. The role also leads hardware/software co-design, pre-silicon and post-silicon technical escalation, customer enablement, cross-functional alignment, and engineering process improvements. Occasional domestic and international travel is expected. This role is not eligible for visa sponsorship.

Requirements

  • Engineering experience in dGPU/SoC platform architecture, hardware engineering, systems software, firmware, or low-level driver development used to bring new silicon to market; the posting gives experience levels of 3+, 7+, or 10+ years.
  • Proven hardware/software co-design experience, including defining hardware-software interfaces, analyzing system performance bottlenecks, and debugging complex multi-layer hardware, firmware, and software issues.
  • Technical leadership experience is specified as 0, 0, or 2+ years, with demonstrated ability to drive technical alignment and resolve ambiguity across multidisciplinary teams.
  • Solid understanding of enterprise manageability standards such as IPMI, iDRAC, and iLO, as well as system telemetry frameworks and production monitoring stacks such as Prometheus, Grafana, and OpenTelemetry.
  • Hands-on experience with containerized GPU deployment and orchestration on Linux and Windows, including Docker, Podman, and Kubernetes, including K3s for edge nodes.
  • Experience with Slurm or another cluster scheduler for batch and HPC environments.
  • Excellent written and verbal communication skills, including the ability to explain architectural trade-offs to hardware and software audiences.
  • Willingness to travel domestically and internationally occasionally.

Nice To Haves

  • Knowledge of ML/AI workloads and model architectures such as Transformers, Stable Diffusion, CNNs, and UNet, including GPU acceleration optimization with libraries such as ROCm or CUDA.
  • Hands-on graphics architecture experience with DirectX 12, Vulkan, ray tracing pipelines, neural rendering, or game engine performance profiling.
  • Experience with pre-silicon simulation or emulation environments, server board design, or power integrity analysis.
  • Experience taking AI workloads from prototype to production, including installing and integrating serving stacks such as vLLM or SGLang, scaling across nodes, tuning throughput and latency, and handing over operations to customers.
  • An advanced degree (M.Sc., M.Eng., or Ph.D.) in Electrical Engineering, Computer Engineering, Computer Science, or a related field.

Responsibilities

  • Drive end-to-end dGPU platform definition, evaluating SoC design, power delivery, thermal envelopes, board-level signal and power integrity, and form factors for server, edge, and client systems.
  • Assess memory architecture requirements, including GDDR, LPDDR, and HBM, and optimize high-speed interconnect topologies for bandwidth and system efficiency.
  • Define hardware telemetry, power-monitoring, and diagnostics hooks for integration with enterprise manageability platforms such as iDRAC, iLO, and IPMI.
  • Translate system architecture concepts into software requirements spanning firmware, drivers, runtimes, ROCm libraries, tools, and application stacks across AI, media, visualization, and simulation workloads.
  • Create long-term software architecture plans that integrate with Kubernetes orchestration, AI frameworks, and enterprise management tools.
  • Author reference architectures, sizing guidance, and tuning guides for customers, ISVs, and systems integrators.
  • Support application porting and migration onto the platform and serve as an escalation point for failures in live customer software stacks.
  • Lead hardware/software interface definition so silicon features support software requirements and firmware, driver, and library designs reflect hardware constraints.
  • Serve as a primary technical escalation point during pre-silicon modeling and early post-silicon bring-up, debugging issues across hardware, firmware, drivers, and application software.
  • Guide development of diagnostics, pre-silicon emulators, and silicon validation tools to accelerate bring-up schedules.
  • Collaborate across SoC architecture, design verification, hardware engineering, driver development, performance libraries, and product management.
  • Champion AI-assisted tools for system modeling, code development, review, and documentation, establishing standards for traceability and validation.
  • Document reusable architectural patterns, bring-up playbooks, and hardware-software design practices.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service