Senior AI Infra Architect - GPU & Low-Latency Serving

ThoughtWorks; Singapore; On-site; SGD 80,000 - 100,000; Full time

Job summary

A leading technology consultancy in Singapore is seeking a skilled infrastructure engineer to design and manage GPU-based AI systems. In this role, you will architect scalable systems using advanced tools and mentor teams in best practices. Ideal candidates will have expertise in GPU tech, orchestration frameworks, and a passion for innovative AI solutions. Join an environment that supports professional growth and enables you to make impactful contributions to clients' AI strategies.

Benefits

Career development programs

Collaborative work culture

Qualifications

• Expertise in GPU-based infrastructure (H100, GB200) for AI applications.
• Strong knowledge of orchestration frameworks like Kubernetes and Ray.
• Experience with building resilient AI systems and monitoring tools.

Responsibilities

• Design GPU infrastructure for cloud and on-site environments.
• Automate deployment and provisioning of AI resources.
• Lead technical engagements with clients to align AI goals.

Skills

GPU-based infrastructure expertise

Kubernetes knowledge

Involvement in AI systems performance tuning

Infrastructure automation proficiency

Experience with monitoring tools

Tools

Terraform

Helm

CI / CD pipelines

Prometheus

Grafana

OpenTelemetry

Job description

A leading technology consultancy in Singapore is seeking a skilled infrastructure engineer to design and manage GPU-based AI systems. In this role, you will architect scalable systems using advanced tools and mentor teams in best practices. Ideal candidates will have expertise in GPU tech, orchestration frameworks, and a passion for innovative AI solutions. Join an environment that supports professional growth and enables you to make impactful contributions to clients' AI strategies.