AI Infrastructure Lead (AI Inference Platform)

Gateway Search Pte Ltd; Singapore; On-site; SGD 220,000 - 340,000; Full time

Job summary

Gateway Search Pte Ltd is seeking a founder-level AI Infrastructure Lead to own the end-to-end AI inference platform from Singapore. You will architect the stack, guide engineering standards and build a high-performing team responsible for GPU‑based compute, backend services and platform operations.

You will stay hands-on while coordinating with global infrastructure teams, driving design reviews and delivering scalable, reliable systems in a fast-growing APAC environment.

Qualifications

• 8+ years in software engineering, distributed systems or AI infrastructure.
• Track record delivering production-grade distributed systems or platforms.
• Strong understanding of AI infrastructure and GPU computing.
• Hands-on experience with Linux, Kubernetes, containers and cloud infra.
• Strong programming skills in Python, Go, C++ or similar.
• Excellent English communication across global teams.

Responsibilities

• Own end-to-end architecture of the AI inference platform, including GPU infra and backend systems.
• Lead design reviews, resolve performance bottlenecks and assess risks.
• Hire, mentor and grow an engineering team; set standards and review code.
• Collaborate with global teams to align objectives and execution plans.

Skills

Distributed systems

AI infrastructure

Kubernetes

Python

Go

C++

Linux

Cloud infrastructure

Tools

Containers

GPU compute

TensorRT-LLM

Job description

AI Infrastructure Lead (AI Inference Platform)

About Our Client

Our client is a publicly listed AI compute and data centre infrastructure provider and an NVIDIA partner. It runs the latest generations of GPU clusters, from H100 to GB300, across North America, Europe and Asia. Its customers include frontier AI labs, hyperscalers and leading internet companies, which buy high-performance GPU compute and full-lifecycle data centre capacity.

As part of its APAC expansion, the company is building a new AI inference platform from Singapore and is hiring a founding technical leader to own it end to end.

Why This Role

• You join at the ground floor and shape the architecture, tech stack and engineering culture from day one


• You build and lead the Singapore engineering team


• You work hands‑on with large-scale, latest‑generation GPU infrastructure


• You work closely with the global infrastructure and engineering teams of a listed company

What You’ll Do

Architecture & Technical Direction

• Own the end‑to‑end architecture of the platform, covering AI inference services, GPU infrastructure, backend systems and platform operations


• Evaluate technology options and lead key technical decisions


• Set engineering standards, documentation practices and architecture best practices


• Reuse existing global infrastructure and engineering capabilities where it makes sense

Hands‑on Engineering & Delivery

• Stay hands‑on in system development, infrastructure integration and complex problem‑solving


• Lead design reviews and resolve performance bottlenecks, scalability issues and technical risks


• Drive delivery while balancing performance, reliability, security and infrastructure cost

Team Building

• Hire, mentor and grow a high‑performing engineering team


• Define technical competency standards and lead technical interviews


• Set up engineering workflows and code review standards, and build a culture of ownership and continuous improvement


• Work with global infrastructure, engineering and business teams, and coordinate dependencies across them


• Turn business objectives into technical priorities and execution plans


• Communicate architecture decisions, progress and risks to stakeholders

What You Bring

• 8+ years in software engineering, distributed systems, cloud or AI infrastructure, including technical leadership experience


• A track record of designing and delivering production‑grade distributed systems or infrastructure platforms


• Strong understanding of AI infrastructure, GPU computing and inference platform architecture


• Hands‑on experience with Linux, Kubernetes, containers and modern cloud infrastructure


• Strong programming skills in Python, Go, C++ or a comparable language


• Sound architectural judgement and the ability to assess engineering talent


• Excellent English communication and experience working across global teams

Nice to Have

• Experience building or operating AI inference platforms, GPU cloud or large‑scale compute infrastructure


• Familiarity with vLLM, TensorRT-LLM or SGLang


• Knowledge of GPU resource scheduling, distributed inference, model serving and performance optimisation


• Experience with platform reliability, observability and infrastructure automation


• Experience building teams or platforms from an early stage


• A background in AI infrastructure, cloud platforms, HPC or high‑growth tech companies

All applications will be treated with strictest confidence. We regret to inform you that only shortlisted candidates will be notified.

EA Licence No: 19C9807

Registration No: R22110556 (ZHOU DONGYANG)