Senior Data Scientist, Network Intelligence

Xplore Inc•Oni, PE

About The Position

As a Senior Data Scientist, you will develop and deploy the predictive analytics and ML models that enable Xplore's network to become self-monitoring and increasingly self-optimizing across Fiber, Fixed Wireless, and Satellite platforms. You will translate high-resolution network telemetry, operational event data, and customer experience signals into production ML models that reduce incident response times, improve capacity planning accuracy, and surface network degradation before customers are impacted. This role requires building and operating solutions across both cloud and on-premises environments—not only supporting migration initiatives, but also designing, developing, and deploying capabilities that run natively on-prem where needed. All modeling work is built and served on Databricks, leveraging Gold-tier data assets and integrating with automation and observability pipelines operated by the broader network intelligence squad. You will mentor data scientists on the team and serve as the technical ML authority for the Network Intelligence domain.

Requirements

7-10+ years of applied data science or ML engineering experience in a production environment.
Strong proficiency in Python for data science: pandas, scikit-learn, XGBoost, and PyTorch or TensorFlow.
Hands-on experience building and deploying data science or ML solutions across both cloud and on-premises environments, including Databricks for model development, MLflow for experiment tracking, and Delta Lake for feature management.
Solid foundation in statistical modeling, time-series analysis, and anomaly detection methods.
Experience working with large-scale, high-frequency telemetry or event-driven datasets.
Familiarity with SHAP or other model explainability frameworks for stakeholder communication.
Ability to frame business problems as ML problems and communicate results clearly to non-technical audiences.
Strong communication skills and demonstrated mentorship experience.

Nice To Haves

Background in network operations, telecommunications, or infrastructure analytics.
Familiarity with network performance metrics: throughput, latency, packet loss, RSRP/RSRQ, SINR, or equivalent RAN KPIs.
Exposure to reinforcement learning or simulation-based optimization for network decisioning.
Experience with Databricks Feature Store or equivalent feature platform tooling.
Databricks Certified Machine Learning Professional.
Bachelor's or Master's degree in Computer Science, Statistics, Applied Mathematics, or a related field.

Responsibilities

Develop and deploy ML models for anomaly detection, predictive failure, capacity forecasting, and network performance degradation using Databricks and MLflow.
Build feature engineering pipelines from network telemetry (RAN KPIs, alarms, traffic counters, customer experience data) using PySpark and Python against Gold-tier Databricks assets.
Design and maintain MLflow experiment tracking, model registries, and retraining pipelines to support production model lifecycle management.
Evaluate and apply appropriate algorithms matched to network time-series and event-driven data patterns: gradient boosting, LSTMs, isolation forest, survival models, and similar.
Build optimization and scoring frameworks to prioritize network interventions: incident severity scoring, site risk tiering, maintenance urgency ranking.
Integrate model outputs with automation pipelines so that insights translate into actionable triggers for network operations teams.
Translate complex model outputs into clear narratives, visualizations, and Databricks AI/BI dashboard inputs consumable by engineering, operations, and executive audiences.
Partner with Data Engineers to specify feature datasets, ensure data quality, and align on pipeline dependencies.
Present findings and model performance to Director and VP-level stakeholders with confidence and clarity.