AI Observability Engineer

📋 Description

• Own tools and systems for visibility into AI apps, platforms, and infra performance
• Design, implement, operate observability for AI workloads including LLMs
• Configure AI tracing systems for latency, token usage, cost, quality, prompts, model versions
• Build automation tooling in Python for instrumentation and data collection
• Maintain dashboards and monitoring with Grafana, Prometheus, cloud observability
• Instrument AI platforms for health, usage, cost, and SLOs

🎯 Requirements

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

🎁 Benefits

• Competitive compensation
• Career development and learning opportunities
• Flexible working environment with ownership
• Opportunity to work on impactful AI infrastructure
• Collaborative international teams
• Contribute to next-gen AI platforms