JobHabor
Menu

Edge & Enterprise System Solution Software Architect

AMD · MARKHAM, ON, Canada

Mixed hiring record · median 37 days open

100100

Hiring signal

Actively hiring

Open 5 days · Never reposted · Checked today · How we score

First seen
18 November 2026
Reposted
Not since September 2026
Last checked
Today · still on the employer's board
All reasons
  • 29% of this employer's openings are over 60 days old

In its favour

  • Posted 5 days ago
  • Still listed on the employer's own board

Did you apply?

Edge & Enterprise System Solution Software Architect at AMD. We’ll keep it in your applied jobs, so you can see it later and be warned before applying to the same employer twice.

ADVANCE YOUR CAREER. ADVANCE THE WORLD.

At AMD, we believe technology has the power to solve the world’s most important challenges. From advancing healthcare and scientific discovery to powering AI and the technologies people rely on every day, innovation at AMD is shaping the future.

Whether you’re designing next-gen processors, enabling AI breakthroughs, or bringing leading edge products to market, every role at AMD contributes to something bigger — technology that moves the world forward. Join us and, together, we’ll advance your career.

Responsibilities

As an Enterprise & Edge Solution Architect, you will be responsible for defining, architecting, and deploying the software stack that turns GPU platforms into supportable customer solutions across enterprise data centers, hybrid cloud environments, and edge platforms. In this role, you will bridge the gap between customer workload requirements and the full software stack - runtimes, libraries, frameworks, containers, orchestration, and the applications that run on them. Where an existing product or reference architecture does not meet the requirement, you will prototype, integrate, and adapt the stack to close the gap.

You will partner closely with key enterprise customers, ISVs, systems integrators, and internal engineering teams (driver, runtime, performance library, and platform teams) to translate business needs into robust, scalable, and secure deployment blueprints. Your scope spans the stack from the application down: AI inference and serving, media and visualization pipelines, AI/ML frameworks, ROCm runtimes and libraries, container and orchestration platforms (Kubernetes/K3s), telemetry, security, and the platform and manageability interfaces beneath them (Redfish, IPMI, iDRAC/iLO).

Solution Architecture & Workload Enablement

Customer Discovery & Requirements

Lead technical discovery with customers. Understand their workloads, existing infrastructure, constraints, and operational requirements; translate them into system and software requirements and a sizing basis; and identify where they are not met by an existing product or reference architecture.

Full-Stack Software Architecture

Translate solution requirements into concrete software requirements spanning drivers, runtimes, ROCm libraries, tools, and application layer stacks, across AI, media, visualization, and simulation workloads.

Reference Architectures & Blueprints

Author reference architectures, sizing guidance, and tuning guides that customers, ISVs, and systems integrators deploy from.

Deployment & Operational Design

Deployment & Orchestration Model

Define how the solution is packaged and deployed - container images, driver and user-space version compatibility, Kubernetes and K3s integration, and installation that a customer can automate and repeat.

Resource Management & Multi-Tenancy

Determine how GPUs are shared, partitioned, and scheduled across users and workloads, under Kubernetes and under batch schedulers such as Slurm.

Telemetry, Security & Lifecycle

Specify how the solution is monitored, updated, and secured in service across data center and distributed edge sites: GPU telemetry into the tools operations teams use (Prometheus, Grafana, OpenTelemetry) and into enterprise manageability platforms (Redfish, IPMI, iDRAC/iLO); signed images and attestation; supported version matrices and a CVE and patch response model.

Application Stack & Solution Integration

Inference & Serving

Deploy, scale, and tune inference serving stacks (for example vLLM, SGLang, ONNX Runtime, Triton) for throughput, latency, and cost, including batching and quantization choices.

Framework Enablement

Ensure AI frameworks and their dependencies run and perform correctly on the platform, and validate functional and numerical behavior across driver, library, and framework versions.

Application Porting & ISV Enablement

Support customer and ISV application porting and migration onto the platform, including CUDA-to-HIP migration, and own the performance and correctness validation that follows.

Prototyping & Integration

Build working prototypes and reference implementations for customer solutions. Integrate AMD and third-party components, adapt and extend existing software where required, and work with the owning engineering teams to close gaps in the product stack.

Cross-Functional Leadership & Process Innovation

Requirements Feedback & Co-Design

Carry workload, deployment, and field requirements back into driver, runtime, library, and silicon planning, and represent the software position in hardware/software interface decisions.

AI-Assisted Development

Champion the use of AI-assisted tools to accelerate solution modeling, code development, review, and documentation, establishing standards for traceability and validation.

Knowledge Capture

Document reusable deployment patterns, tuning playbooks, and solution design best practices to scale engineering capability across product generations.

Required Experience & Qualifications

Experience

10+ years in software engineering or solution architecture, with hands-on experience building and deploying GPU-accelerated solutions in production or customer environments.

GPU Software Stack

Working knowledge of drivers, runtimes, ROCm or CUDA libraries, and frameworks, including version compatibility between layers, and the ability to triage a failure across them in a live customer environment.

ML & AI Workloads

Working knowledge of ML and AI workloads and model architectures (for example Transformers, diffusion models, CNNs), including their compute, memory, and bandwidth behavior, and what that means for system sizing and configuration.

Deployment & Orchestration

Hands-on experience with containerized

GPU deployment and orchestration on Linux and Windows

Docker, Podman, and Kubernetes (including K3s for edge nodes). Experience with Slurm or another cluster scheduler for batch and HPC environments.

Programming & Automation

Proficiency in Python and C++. Working knowledge of infrastructure-as-code and configuration management (for example Ansible or Terraform) for repeatable deployment.

Production Delivery

Proven track record taking

AI or HPC workloads from prototype into production

installing and integrating the stack, scaling it across nodes, tuning throughput and latency, and handing it over for the customer to operate.

Technical Leadership

2+ years in technical leadership roles with a demonstrated ability to drive technical alignment and resolve ambiguity across multi-disciplinary teams (software, platform, drivers, product).

Communication

Excellent written and verbal communication skills, with the ability to articulate complex architectural trade-offs to software, hardware, and customer audiences.

Travel

Willingness to travel domestically and internationally on an occasional basis.Desired & Optional Qualifications

GPU Performance Optimization

Experience optimizing ML/AI workloads on GPU acceleration libraries (e.g., ROCm, CUDA), including library and kernel-level tuning and the use of GPU profiling tools.

Media & Visualization Pipelines

Experience with hardware-accelerated video decode and encode, GStreamer or FFmpeg integration, or graphics and visualization APIs (DirectX 12, Vulkan).

Virtualization & Cloud

Experience with GPU virtualization (SR-IOV, PCIe pass-through, KVM, Hyper-V, or ESXi) and with deploying GPU workloads on public cloud and hybrid environments.

Manageability & Observability

Familiarity with enterprise manageability standards (Redfish, IPMI, iDRAC, iLO) and system telemetry frameworks, and with the software monitoring stacks that operations teams use (for example Prometheus, Grafana, OpenTelemetry).

Platform Hardware

Familiarity with GPU platform specifications - thermals, form factors, memory, and interconnect - and comfort working with platform architects.

Education

Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent practical experience.

Qualifications

Benefits offered are described

AMD benefits at a glance.

AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.

AMD may use Artificial Intelligence to help screen, assess or select applicants for this position. AMD’s “Responsible AI Policy” is available here.

This posting is for an existing vacancy.

Skills

More jobs at AMD

All 26

Similar roles