Senior Solutions Architect - AI/ML GPU PaaS

About the role

A Senior Solutions Architect is sought to help customers deploy, operate and scale AI/ML workloads on a GPU Platform-as-a-Service offering. The role is customer-facing and works closely with platform engineering, MLOps, data science and infrastructure teams to design production-ready AI infrastructure on Kubernetes and GPU-accelerated environments. It is based in Singapore and covers the APAC region.

Key responsibilities

• Design end-to-end AI/ML platform architectures for inference, training and data pipelines, and develop reference architectures for GPU clusters, LLM serving and multi-tenant ML infrastructure.
• Evaluate and recommend inference serving frameworks (vLLM, TGI, Triton, NIM) and advise on GPU fabric topology (NVLink, InfiniBand, RoCEv2).
• Translate customer requirements into platform designs, deliver presentations, workshops and proof-of-concepts, and act as a trusted advisor on strategy, cost and scaling.
• Partner with customer stakeholders, architect networking, identity, observability and security integrations, and monitor and troubleshoot production environments.
• Lead root cause analysis, document reference architectures and implementation guides, and give feedback to Product and Engineering teams.
• Mentor junior team members and travel regularly across APAC; proficiency in spoken Mandarin is required.

Required profile

• 8+ years in infrastructure, platform or solutions engineering, with 3+ years focused on AI/ML infrastructure or MLOps.
• Deep Kubernetes expertise and hands-on experience with NVIDIA GPUs (H100/H200/B200 preferred).
• Experience with LLM inference serving and optimisation, and familiarity with GPU Operator, MIG, SR-IOV and network fabrics.
• Experience with at least one programming language (Python or Go) and strong scripting and automation skills.
• Experience with AWS, Azure or GCP, including networking, IAM and managed Kubernetes.
• Proven troubleshooting, communication and customer-facing skills, and willingness to travel across APAC.

Required skills

• Kubernetes, distributed training (NCCL, tensor and pipeline parallelism)
• vLLM, NIM, TGI, PyTorch, TensorFlow (preferred)
• Prometheus, Grafana, OpenTelemetry
• Preferred: CKA, CKAD, AWS/Azure/GCP Solutions Architect certifications

What we offer

• Competitive base salary with equity incentives and performance bonuses
• Health, dental and vision insurance
• Flexible working model