AI Infrastructure Lead (LLM Inference Platform, token factory)

Gateway Search Pte Ltd; Singapore; Presencial; SGD 180 000 - 260 000; Tempo integral

Resumo da oferta

Gateway Search Pte Ltd is seeking a hands‑on Technical Lead / AI Infrastructure Lead in Singapore to drive a next‑generation AI inference and computing platform. You will define system architecture, lead technical decisions, and oversee engineering execution while building a high‑performing team.

The role emphasizes distributed systems, cloud-native tech, and GPU infrastructure with strong collaboration across global engineering groups and business stakeholders.

Qualificações

• 8+ years of experience in software engineering, distributed systems or AI infrastructure.
• Proven track record in designing scalable, production-grade platforms.
• Strong expertise in cloud-native technologies and GPU infrastructure.
• Hands-on leadership in architecture reviews and execution.

Responsabilidades

• Own the overall technical architecture and system design for the platform.
• Lead technical decisions, perform design reviews, and guide delivery.
• Address performance, scalability, security, and cost trade-offs.
• Build and mentor a high-performing engineering team; drive recruitment.
• Collaborate with global teams and translate business needs into concrete priorities.

Conhecimentos

Distributed systems

Cloud infrastructure

AI infrastructure

Python

Go

C++

Kubernetes

Technical leadership

Ferramentas

Kubernetes

Containers

Descrição da oferta de emprego

A global AI computing and digital infrastructure company specializing in high-performance GPU computing, AI infrastructure, and scalable data center solutions. With operations across multiple international markets, the company provides advanced computing infrastructure and end-to-end solutions to support AI innovation, large-scale model deployment, and enterprise computing needs.

The Role

We are seeking a hands-on Technical Lead / AI Infrastructure Lead to spearhead the development of a next-generation AI inference and computing platform in Singapore. This is a key technical leadership role responsible for defining system architecture, driving technology decisions, overseeing engineering execution, and building a high-performing technical team.

The ideal candidate brings strong expertise in distributed systems, cloud-native technologies, and AI infrastructure, with the ability to translate business requirements into scalable, practical solutions. The successful candidate will also play a critical role in technical hiring, team development, and collaboration with global engineering teams.

Add specific AI infrastructure requirementsClarify hands-on technical expectations

Key Responsibilities

1. Technical Architecture & Decision-Making

• Own the overall technical architecture and system design for the Token Factory platform.
• Evaluate technology options, make architectural recommendations, and lead key technical decisions.
• Design scalable, reliable systems integrating AI inference services, GPU infrastructure, backend components, and platform operations.
• Establish engineering standards, technical documentation, and architecture best practices.
• Identify opportunities to leverage existing global infrastructure and engineering capabilities.

2. Hands-on Engineering & Project Delivery

• Provide hands‑on technical leadership in system development, infrastructure integration, and complex technical problem‑solving.
• Lead technical design reviews and guide implementation decisions.
• Identify and address performance bottlenecks, scalability challenges, and technical risks.
• Drive engineering execution and ensure delivery against agreed project requirements.
• Balance performance, reliability, security, and infrastructure cost efficiency.

3. Engineering Team Building & Technical Assessment

• Lead technical interviews and candidate assessments for future engineering hires.
• Define technical competency requirements and support engineering recruitment decisions.
• Build, mentor, and guide a high-performing engineering team.
• Establish engineering workflows, code review standards, and knowledge-sharing practices.
• Foster a culture of technical ownership, accountability, and continuous improvement.

4. Global Collaboration & Stakeholder Management

• Collaborate with WhiteFiber's global infrastructure, engineering, and business teams.
• Coordinate technical resources, dependencies, and responsibilities across teams.
• Translate business requirements into technical priorities and execution plans.
• Communicate architecture decisions, engineering progress, and technical risks to stakeholders.

Requirements

• Experience: 8+ years of relevant experience in software engineering, distributed systems, cloud infrastructure, or AI infrastructure, including technical leadership experience.
• System Architecture: Proven experience designing and delivering scalable, production-grade distributed systems or infrastructure platforms.
• AI Infrastructure: Strong understanding of AI infrastructure, GPU computing concepts, and AI inference platform architecture.
• Cloud-native Technologies: Hands‑on experience with Linux, Kubernetes, containers, and modern cloud infrastructure.
• Programming: Strong programming capabilities in Python, Go, C++, or comparable languages.
• Technical Leadership: Ability to make sound architecture decisions, lead technical reviews, and evaluate engineering talent.
• Execution: Demonstrated ability to independently solve complex technical problems and drive engineering delivery.
• Communication: Strong English communication and ability to collaborate effectively across global teams.

Preferred Qualifications

• Experience building or operating AI inference platforms, GPU Cloud, or large-scale compute infrastructure.
• Familiarity with LLM inference frameworks such as vLLM, TensorRT-LLM, or SGLang.
• Understanding of GPU resource scheduling, distributed inference, model serving, and performance optimization.
• Experience with platform reliability, observability, and infrastructure automation.
• Experience building engineering teams or establishing technical platforms from an early stage.