We test and monitor cloud data centers (DC) and network inside (intra-DC) and network between DC (backbone site-to-site). The problem arises with potential degradations of performance during outages, maintenance, anomalies and higher than usual traffic. We want to be able to ideally predict, and in any other case respond fast to these events. We want to efficiently use anomaly detection on the given data. We want to correlate the data and predict outages by training ML models and using them. We want to build models of usage of the network which characterize traffic in dependence of measured metrics (such as jitter, delay). The data we posses is performance data between and inside AZ (availability zones) inside DC, and the data from the backbone network between sites. We have consistent data from 3 DC (two from Vienna - ATVIEF1 and ATVIEF2, and one from Salzburg - ATSALF1).
Is your team interested in participating in an interview?
Y
Optional: Expand on your technology expertise
Software and data engineers building ETL, data pipeline implementation, skilled in Python, backend and frontend knowledge. Also some basic ML skills and experience.
