Starry Recruitment Hiring! Full Time Solution Architect (GPU Cluster) in - Ricebowl

About the Role

We are looking for a Solution Architect to support enterprise customers using GPU cloud infrastructure for AI inference workloads. This role will act as the key technical point of contact for Western / English-speaking customers, helping them design, deploy, and optimize AI workloads on GPU cloud platforms.

The ideal candidate should have a strong background in GPU infrastructure and networking, with good understanding of cloud infrastructure and AI inference workloads.

Key Responsibilities

• Act as the technical point of contact for enterprise customers using GPU cloud / AI infrastructure services.
• Understand customer requirements around AI inference workloads and translate them into practical technical solutions.
• Design GPU cloud solutions covering GPU compute, networking, storage, deployment architecture, monitoring, and reliability.
• Support technical discussions, solution presentations, PoCs, customer onboarding, and troubleshooting.
• Work closely with engineering, product, and business teams to ensure customer requirements are delivered effectively.
• Help customers optimize inference performance, GPU utilization, network performance, cost efficiency, and deployment reliability.
• Provide customer feedback to internal teams to improve platform capabilities and service quality.

Requirements

• 5–10 years of experience in solution architecture, cloud infrastructure, AI infrastructure, GPU infrastructure, networking, DevOps/SRE, or related technical roles.
• Strong understanding of GPU infrastructure, AI inference workloads, model deployment, or LLM serving.
• Solid experience in networking, including cloud networking, data center networking, routing, load balancing, or high-performance network architecture.
• Experience with Kubernetes, Linux, containers, monitoring, and production system troubleshooting.
• Good customer-facing communication skills, especially with English-speaking enterprise customers.
• Able to explain complex technical topics clearly to both technical and business stakeholders.
• Singapore-based candidates are preferred.

Preferred Qualifications

• Experience with GPU cloud, AI inference platforms, HPC, or large-scale compute infrastructure.
• Familiarity with NVIDIA GPUs, CUDA, vLLM, Triton, Kubernetes GPU scheduling, InfiniBand, RoCE, or similar technologies.
• Storage infrastructure experience is a plus, but not the top priority.
• Prior experience supporting international or Western enterprise customers.
• Bilingual communication skills are a plus.