AI Observability Engineer

📋 Description

• Own tools, processes, and systems providing visibility into AI applications, platform services, and
• Design, implement, and operate observability solutions for AI workloads, including LLM and agent
• Configure and maintain AI tracing systems to capture latency, token usage, cost, quality metrics
• Develop internal tooling and automation using Python for instrumentation and data collection.
• Build and maintain dashboards, metrics, and monitoring solutions using Grafana, Prometheus, and
• Instrument AI platforms to provide visibility into health, usage, performance, cost, and SLOs

🎯 Requirements

• 5–8 years in observability, SRE, DevOps, or cloud engineering roles.
• Strong hands-on experience with Azure Monitor, Application Insights, Log Analytics, and Managed
• Experience with Langfuse, Grafana, and Prometheus for AI/application monitoring.
• Solid Terraform and CI/CD practices; strong Python skills for automation and tooling development.
• Familiarity with ML workloads and AI observability requirements; knowledge of logs, metrics
• Ability to work effectively in distributed, fast-paced, collaborative environments; intermediate or

🎁 Benefits

• Competitive compensation package.
• Career development and continuous learning opportunities.
• Flexible working environment with ownership and autonomy.
• Opportunity to work on impactful AI infrastructure projects with international teams.
• Collaborative culture in a highly skilled environment.