AI Observability Engineer

📋 Description

• Own tools, processes, and systems for AI observability across applications, platforms, and infra.
• Design, implement, and operate observability solutions for AI workloads (LLMs and agents).
• Configure AI tracing to capture latency, token usage, cost, quality, prompt analytics, model
• Develop internal tooling using Python for instrumentation and data collection.
• Build dashboards and monitoring with Grafana, Prometheus, and cloud observability platforms.
• Instrument AI platforms to provide health, usage, performance, and SLO visibility.

🎯 Requirements

• 5–8 years in observability, SRE, DevOps, or cloud engineering roles.
• Hands-on experience with Azure Monitor, Application Insights, Log Analytics, and Grafana.
• Experience with Langfuse, Grafana, and Prometheus for AI/app monitoring.
• Strong Terraform and CI/CD skills.
• Strong Python for automation, instrumentation, exporters, and tooling.
• Familiarity with ML workloads and AI observability requirements.

🎁 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.
• Collaborative culture with international teams.
• Chance to contribute to next-gen AI platforms.