Job Description

Joining Razer will place you on a global mission to revolutionize the way the world games. Razer is a place to do great work, offering you the opportunity to make an impact globally while working across a global team located across 5 continents. Razer is also a great place to work, providing you the unique, gamer-centric #LifeAtRazer experience that will put you in an accelerated growth, both personally and professionally.
Job Responsibilities :
We are looking for Site Reliability Engineers (SRE) to join our AI Software team. In this role, you will ensure the reliability, performance, scalability, and operational excellence of AI products, model-serving infrastructure, and backend API systems. You'll work closely with software engineers, AI teams and release teams to automate operations, enhance observability, and streamline deployments in a cloud-scale environment. This role is ideal for someone who enjoys building resilient systems, solving complex infrastructure problems, and supporting AI workloads in production.
Essential Duties and Responsibilities
Administer, monitor, and manage cloud-scale production environments for AI model APIs, backend services, and high-traffic web systems serving global users.
Design and implement fault-tolerant, autoscaling cloud architectures tailored for AI inference workloads, including GPU-based environments and software products.
Build automated self-recovery systems to ensure high availability, rapid failover, and cost-efficient resource usage for all software products.
Manage and monitor AI model-serving platforms, inference engines, vector databases, data pipelines, software applications
Ensure reliability and uptime for experimental, production AI software environments.
Implement and maintain comprehensive monitoring, logging, and alerting for all AI and backend services.
Reduce MTTR through actionable alerts, runbooks, and automated diagnostics.
Automate infrastructure using IaC (Terraform/CloudFormation) and configuration management.
Improve release workflows and integrate with QA for smooth handoff to Release Candidate testing.
Work closely with software engineering, ML engineering, and release management to enhance operational procedures, deployment processes, and incident response workflows.
Participate in on-call rotations, incident reviews, and continuous improvement initiatives..
Pre-Requisites :
Qualifications
4+ years of relevant experience in SRE, DevOps, infrastructure engineering, or cloud operations
Experience operating production services with significant availability or scaling demands.
Strong knowledge in Web Technologies such as HTTP, REST, SSL, Load Balancers, Web Proxies (NGINX)
Comfortable with Linux and Docker administration
Basic knowledge in AWS, CI/CD (Jenkins), IaC (Terraform), Container Orchestration (AWS ECS or K8s), Version Control (Git), Database (mySQL, noSQL)
Strong ability to code and script ( preferably Bash scripting and Python)
Ability to use or quickly pick up a wide variety of open source technologies and automation tools
Understanding of GPU-based workloads and resource scheduling.
Familiarity with vector databases, embeddings, and inference pipeline
Comfort with frequent, incremental code testing and deployment
Must have good analytical skills to debug deployment problems without taking help from developers
Deep hands-on technical expertise and problem-solving skills
Ability to work in a collaborative, technically challenging environment with rapidly changing requirements.
Education & Experience
Has a Bachelor's or Master's degree in computer science, AI or similar discipline from an accredited institution
Travel Requirements
Role based in ?Singapore office? and may require up to 1 travel trip per year.
Are you game?

Skills Required