Senior Solutions Engineer: AI/ML GPU-Kubernetes Architect

Rafay Systems; United States; On-site; USD 140,000 - 170,000; Full time

Job summary

Rafay Systems seeks a Senior Solutions Engineer who partners with enterprise customers to architect, deploy, and optimize Rafay platform-based cloud-native infrastructure and Kubernetes ecosystems.

The role focuses on leading customer engagements, designing scalable solutions, and guiding teams through GPU-accelerated AI/ML workloads with performance and reliability in mind. Strong communication is essential.

Qualifications

• 10+ years of experience in customer-facing technical roles, including implementation or consulting.
• Hands-on AI/ML engineering experience with model inference and deployment workflows.
• Hands-on experience with NVIDIA GPU infrastructure (H100/H200 preferred).
• Familiarity with GPU Operator, MIG, SR-IOV, and GPU fabric/networking fundamentals.
• Experience with LLM inference serving frameworks such as vLLM, TGI, or Triton.
• Strong Kubernetes and cloud-native environment expertise.
• Excellent written and verbal communication abilities.
• Deep troubleshooting skills across networking, virtualization, container orchestration, and public cloud platforms.
• Linux systems administration and distributed systems knowledge.
• Proven ability to lead technical projects and manage multiple engagements.

Responsibilities

• Lead customer implementation engagements.
• Gather requirements, perform architecture reviews, and design solutions.
• Design Rafay platform deployments across public, private, and hybrid clouds.
• Troubleshoot complex infra, networking, Kubernetes, and virtualization issues.
• Collaborate with CS, Product, and Engineering on technical challenges.
• Manage customer issues within SLAs and set expectations.
• Create technical docs, runbooks, and implementation guides.
• Mentor junior engineers and drive process improvements.
• Stay current on Rafay capabilities and industry trends.
• Deploy GPU-accelerated Kubernetes clusters for AI/ML workloads with GPU Operator, MIG, and SR-IOV setup.
• Validate LLM inference stacks (vLLM, TGI, Triton).
• Troubleshoot GPU cluster health, utilization, and GPU fabric networking.
• Configure GPU observability with DCGM and OpenTelemetry; use Grafana dashboards.
• Advise on distributed training and inference topology for NVIDIA GPUs.

Skills

Customer-facing experience

Technical leadership

Kubernetes

Cloud-native architecture

AI/ML engineering

Linux administration

NVIDIA GPU infrastructure

LLM inference serving

Education

Bachelor's degree in Computer Science, Engineering, IT, or equivalent experience

Tools

NVIDIA GPU Operator

MIG

SR-IOV

DCGM

Prometheus/Grafana

Job description

Rafay Systems seeks a Senior Solutions Engineer who partners with enterprise customers to architect, deploy, and optimize Rafay platform-based cloud-native infrastructure and Kubernetes ecosystems.

The role focuses on leading customer engagements, designing scalable solutions, and guiding teams through GPU-accelerated AI/ML workloads with performance and reliability in mind. Strong communication is essential.