Senior Site Reliability Engineer

What you'll do

• Design, build, and operate large-scale, distributed, fault-tolerant systems and associated IaC, CI/CD, and automation tooling.
• Manage the patch, vulnerability, and golden-image lifecycle across the fleet through triage, remediation, and automation.
• Build and operate ML inference infrastructure, including model serving, GPU workloads, and language model gateways.
• Execute multi-quarter initiatives such as compute rationalization, cloud re-platforming, and ML platform migration.
• Establish infrastructure standards and security guardrails for agentic AI and develop internal agent tooling.
• Troubleshoot and resolve technical challenges across web services, databases, pipelines, and ML systems.
• Participate in an on-call rotation to provide incident response and operational support.

What we're looking for

• BSc in Computer Science or equivalent experience in a practical setting.
• Proficiency in Python with familiarity in PHP, Node.js, or Ruby.
• Experience deploying and operating ML inference pipelines like SageMaker, OpenAI, or Bedrock in production.
• Experience operating cloud-native compute using AWS EC2 Auto Scaling Groups and Kubernetes.
• Experience with vulnerability/patch management and AMI/golden-image lifecycle automation at fleet scale.
• Strong debugging skills on distributed systems.
• Willingness to participate in an on-call rotation.
• Production ML operations, GPU-backed compute tuning, or relational database operations experience (preferred).