Description

Design, build, and maintain scalable AIOps platforms using Lakehouse architectures and real-time streaming pipelines to drive anomaly detection and incident forecasting.

This role is on-site.

Responsibilities

• Architect and manage scalable data pipelines using Kafka, Flink/Spark, and Delta Lake/Iceberg for large-scale observability datasets.
• Develop and deploy machine learning models for anomaly detection, root-cause analysis, and incident forecasting.
• Build real-time streaming inference pipelines to enable low-latency anomaly scoring and automated alert generation.
• Own the full ML lifecycle, including feature engineering, model monitoring, drift detection, and automated retraining via MLOps.
• Enforce data quality governance and schema standards while integrating AIOps insights into incident management systems.

Required Skills

• 10+ years of experience in data engineering, machine learning, and AIOps/observability platforms.
• Strong expertise in Apache Kafka and streaming frameworks such as Flink or Spark.
• Hands-on experience with Lakehouse architectures, specifically Delta Lake or Apache Iceberg.
• Proven track record of building and deploying anomaly detection and time-series ML models.
• Deep knowledge of MLOps practices, including feature stores, model monitoring, and automated retraining.
• Bachelor’s or master’s degree in Computer Science, Data Engineering, Machine Learning, or a related field.

Key Skills

Education

Any Graduate