About The Position

This role focuses on Data Analysis, Insight Generation, Machine Learning Modeling, and Data Engineering Automation. The Data Engineer will analyze large-scale wireless (RAN, Core) and IEN network alarm data from OSS/NMS systems to identify patterns, trends, and recurring fault signatures. They will develop KPIs and dashboards to track network health and fault trends. Additionally, the role involves building models for alarm correlation and noise reduction, performing root cause analysis (RCA), anomaly detection, and predictive fault/failure forecasting using supervised and unsupervised learning techniques. The Data Engineer will also be responsible for cleaning, normalizing, and enriching alarm data from multiple sources, integrating data from OSS, EMS, NMS, CMDB, and performance systems.

Requirements

  • PySpark/Apache Flink
  • Python for Data Science
  • 5G Wireless Networks
  • 8-10 years of experience
  • Data Analysis
  • Insight Generation
  • Machine Learning Modeling
  • Data Engineering Automation
  • Analyze large-scale wireless (RAN, Core) and IEN network alarm data from OSS/NMS systems
  • Identify patterns, trends, and recurring fault signatures across network domains
  • Develop KPIs and dashboards to track network health and fault trends
  • Build models for Alarm correlation and noise reduction
  • Root cause analysis (RCA)
  • Anomaly detection
  • Predictive fault and failure forecasting
  • Apply supervised and unsupervised learning techniques (clustering, classification, time-series analysis)
  • Clean, normalize, and enrich alarm data from multiple sources
  • Integrate data from OSS, EMS, NMS, CMDB, and performance systems

Nice To Haves

  • Keyword:

Responsibilities

  • Analyze large-scale wireless (RAN, Core) and IEN network alarm data from OSS/NMS systems
  • Identify patterns, trends, and recurring fault signatures across network domains
  • Develop KPIs and dashboards to track network health and fault trends
  • Build models for Alarm correlation and noise reduction
  • Perform Root Cause Analysis (RCA)
  • Conduct Anomaly detection
  • Forecast predictive faults and failures
  • Apply supervised and unsupervised learning techniques (clustering, classification, time-series analysis)
  • Clean, normalize, and enrich alarm data from multiple sources
  • Integrate data from OSS, EMS, NMS, CMDB, and performance systems
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service