Site Reliability Engineer For Llm Platforms Toronto

We're seeking a Site Reliability Engineer to enhance our real-time transcription and summarization platforms powered by Large Language Models.

Your role will be vital in ensuring system reliability and performance. As an SRE, you will confront the complexities inherent in handling diverse real-time communication formats. Your daily tasks will include monitoring system health, optimizing infrastructure, and managing incident responses.

You will implement automation to maintain productive, low‑latency data pipelines across various platforms.

Key Responsibilities

• Monitor and manage the health of LLM platforms
• Improve performance through enhanced observability
• Respond effectively to incidents when they arise
• Scale infrastructure to meet growing operational needs
• Automate processes for reliable data handling

Requirements

• Expertise in Dynatrace along with RUM
• Familiarity with ElasticSearch and Grafana
• Experience with OpenShift and OpenTelemetry
• Knowledge of MongoDB and PostGres systems
• Proficient in GitHub Actions CI/CD, HashiCorp Vault

Become a crucial part of our team dedicated to reliability and performance.