Data centre ‘building doctor’: He keeps power, cooling systems running
He clocks 10,000 steps daily to inspect critical equipment across six floors.
Keith Fong, a 29-year-old mechanical engineer, works as a team lead in the site operations department of STTGDC data centre in Tai Seng, Singapore. His primary responsibility is to maintain the constant supply of power and cooling needed to support AI workloads around the clock at the 20-strong department. STTGDC operates six data centres in Singapore and over 100 globally.
The role of a data centre engineer involves monitoring and maintaining the physical infrastructure and critical systems of a data centre, which houses computer servers, storage systems and networking equipment. With no downtime allowed, these engineers must ensure uninterrupted cooling and power supply. As a remote hands service, Keith can also check equipment, investigate faults, and troubleshoot issues on behalf of customers.
A data centre outage can have significant effects on businesses and consumers, with knock-on effects across the economy. To prevent this, the engineers have strict security procedures, including a fence intrusion detection system, mantrap access control, and on-site security guards.
STTGDC provides colocation services, renting out space, power, and cooling services to companies, and the IT equipment inside the data centre belongs to the customers. The growing use of AI has led to the need for more powerful servers, increasing demand for colocation, connectivity, and support services.
The engineers rely on various tools, such as sensors like the VESDA system, which detects very small concentrations of smoke particles. The engineers have resilience measures in place, including backup generators and uninterruptible power supplies, to ensure cooling is not affected during power outages. They are also trained emergency responders, capable of administering first aid, cardiopulmonary resuscitation, and using automated external defibrillators.
Written by urgent.news from Straits Times's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
