Head of Platform Engineering

About the Role

We are seeking a seasoned Head of Platform Engineering to spearhead our client's AI infrastructure development and maintenance in Singapore. This leadership role entails overseeing the design, deployment, and continuous improvement of the entire AI platform, emphasizing real-time inference and cloud system operations.

Key Responsibilities

• Direct the architecture, deployment, and upkeep of the AI infrastructure, focusing on real-time inference services alongside cloud environments.
• Manage GPU resources, computational capabilities, and AI model rollouts efficiently across systems.
• Enhance system responsiveness and optimize performance for the end-to-end voice AI processing pipeline.
• Ensure high reliability, consistent availability, and scalability of production systems to support business demands.
• Develop and implement monitoring solutions, incident management protocols, and on-call engineering rotations.
• Improve infrastructure throughput and reduce operational expenses through continuous optimization.
• Lead engineering teams, fostering collaboration to expand and strengthen the AI platform.

Candidate Requirements

• Extensive background in platform engineering, infrastructure management, or distributed system design.
• Demonstrated success in creating large-scale systems characterized by low latency and the capacity to handle high concurrency.
• Hands-on experience with AI inference mechanisms, GPU-based infrastructure, and deploying models in production environments.
• Deep understanding of system reliability engineering, performance tuning, and continuous monitoring.
• Prior involvement in setting formal service-level objectives (SLOs) and managing live production incidents is highly advantageous.
• Strong technical leadership skills paired with active engineering experience leading high-performing teams.