Head of AI Infrastructure & Platform Engineering

mars consulting pte. ltd.; Singapore; On-site; SGD 180,000 - 260,000; Full time

Job summary

Mars Consulting PTE. LTD. seeks a Head of Platform Engineering to drive the AI infrastructure, including real-time inference services and cloud systems. You will oversee GPU resources, capacity planning, and AI model deployment in a fast-paced production environment.

You will ensure reliability and scalability while establishing monitoring, on-call processes, and robust incident response. A hands-on, leadership-focused engineer is essential to guide the growing AI platform.

Qualifications

• Experience in platform engineering or distributed systems.
• Proven ability to build large-scale, low-latency, high-concurrency systems.
• Experience with AI model inference, GPU infrastructure, and production deployment.
• Strong knowledge of reliability, monitoring, and performance optimization.
• Experience establishing SLOs and managing production incidents.

Responsibilities

• Lead the development and management of AI infrastructure, including real-time inference services and cloud systems.
• Manage GPU resources, computing capacity, and AI model deployment.
• Optimize system performance and response times across the voice AI pipeline.
• Ensure system reliability, availability, and scalability in production environments.
• Establish monitoring, incident response, and on-call engineering processes.
• Optimize infrastructure performance and operating costs.
• Lead and collaborate with engineering teams to support the company's growing AI platform.

Skills

Platform engineering

Distributed systems

Low-latency systems

AI model inference

GPU infrastructure

Production deployment

Tools

Kubernetes

Cloud platforms (AWS/GCP/Azure)

Monitoring tools

Job description

Mars Consulting PTE. LTD. seeks a Head of Platform Engineering to drive the AI infrastructure, including real-time inference services and cloud systems. You will oversee GPU resources, capacity planning, and AI model deployment in a fast-paced production environment.

You will ensure reliability and scalability while establishing monitoring, on-call processes, and robust incident response. A hands-on, leadership-focused engineer is essential to guide the growing AI platform.