Key skills
GrafanaPrometheusAIMLJaeger
About this role
Role Overview
- Implement the full observability stack (metrics, logs, traces).
- Create dashboards specific to AI models (drift, performance, latency).
- Establish intelligent alerting systems and SLIs/SLOs for AI applications.
- Develop debugging and troubleshooting tools.
- Implement distributed tracing for AI requests.
Requirements
- Degree or Higher Technician (MECES Level 1 / EQF Level 5) in Information Technology, engineering, mathematics, statistics, or physics.
- Minimum 4 years in observability/monitoring.
- At least 2 years working with ML applications.
- Experience with observability stack (Prometheus, Grafana, Jaeger, ELK).
- Experience with APM tools.
- ML-specific monitoring (model drift, data drift).
- Telemetry and monitoring standards.
- Alerting and incident response.
Tech Stack
- Grafana
- Prometheus
Benefits
- 22 days of vacation + 2 personal leave days.
- Company-provided training to support your development and career progression within the existing career plan.
- Opportunity to attend relevant industry events and conferences.
- Permanent contract (open-ended).
- Job stability and a positive work environment.
- Competitive salary.
- Access to group company benefits.
- Flexible compensation and additional benefits.