Site Reliability Engineer (Machine Learning) - REMOTE

Location: Metro Manila, Philippines | Remote

Employment type: Full-time | Day Shift

About the role

This is a fully remote Site Reliability Engineer (SRE) position with Machine Learning Expertise, partnering with Japan's leading restaurant reservation management platform. You will maintain and scale a 24/7 high-traffic production environment built on AWS and Kubernetes, while bringing SRE and MLOps discipline to machine learning pipelines and inference services.

Key responsibilities

• Maintain and scale a 24/7 high-traffic production environment built on AWS and Kubernetes
• Design, build, and evolve Infrastructure as Code (IaC) using Terraform, Helm, and ArgoCD
• Manage AWS core services, including EKS, EC2, RDS, Fargate, CloudFront, Lambda, and S3
• Drive incident response, proactive monitoring, configuration management, and postmortem processes
• Implement DevOps best practices to boost developer productivity, platform scalability, and system reliability
• Apply SRE discipline to ML infrastructure, ensuring high availability, observability, and performance for model training and inference pipelines
• Support, streamline, and automate ML model deployment pipelines on Kubernetes
• Build monitoring, logging, and alerting systems tailored to production ML models
• Partner with data science and engineering teams to operationalize and scale intelligent features across the platform

About you

• Minimum 2 years of hands-on experience with AWS, with significant depth in AWS EKS, EC2, RDS, Fargate, CloudFront, Lambda, and S3
• Deep experience deploying, managing, and scaling production workloads on Kubernetes
• Strong familiarity with MLOps practices and hands-on Python experience with ML-adjacent tooling (e.g., inference serving, model deployment, ML pipelines)
• Experience in direct software engineering under DevOps/SRE practices, including at least 1 year in a Technical Lead capacity
• Current proficiency in Python (preferred) or Ruby, Elixir, Go, JavaScript, or Rust
• Strong skills in configuration management (YAML, Bash) along with containerization and hypervisor fundamentals
• Track record of operating large-scale production systems with a deep understanding of fault-tolerance and distributed systems failure modes
• Experience in fast-paced startup environments
• Infrastructure as Code & GitOps tools: Terraform, Pulumi, ArgoCD
• Observability stacks: Prometheus, Grafana

Job Ref: RYAN - TT