Data Scientist, NA

Vantage Data Centers•Denver, CO

6d•$140,000 - $150,000•Hybrid

About The Position

This role will be based in Denver, CO. Following our flexible work policy (3 days in-office, 2 days flexible). The Data Scientist plays a critical role in advancing Vantage Data Centers’ analytics, automation, and data-driven decision-making capabilities across North America. This role develops, operationalizes, and scales analytical models that improve forecasting accuracy, optimize data center performance, and enhance operational reliability across Vantage’s rapidly expanding portfolio. The Data Scientist partners closely with Operations, Engineering, Capacity Planning, Finance, Energy & Sustainability, and the Global Data Strategy team to transform raw operational data into actionable insights. This role designs and deploys predictive and prescriptive models that support capacity forecasting, energy optimization, anomaly detection, asset lifecycle management, and customer experience improvements. Operating across regions and collaborating with global stakeholders, the Data Scientist ensures analytical models align with enterprise data architecture, governance standards, and long-term technology strategy. The role contributes to the evolution of Vantage’s data platform, enabling scalable analytics capabilities that support growth, reduce operational friction, and strengthen decision quality across the business.

Requirements

Bachelor’s degree in a quantitative discipline.
5–8+ years of experience in data science, machine learning, and software engineering.
Experience with Full Stack AI assisted development and deployment.
Experience working with large-scale operational, IoT, or industrial datasets strongly preferred.
Background in predictive modeling, time-series forecasting, anomaly detection, and optimization algorithms.
Experience with Azure and Databricks.
Familiarity with data center operations, energy systems, or mission-critical environments preferred.
Experience collaborating with cross-functional teams in matrixed organizations.
Experience deploying models into production environments and integrating with enterprise systems.
Strong proficiency in Python, SQL, and machine learning frameworks (scikit-learn, TensorFlow, PyTorch).
Expertise in time-series modeling, statistical analysis, and data visualization.
Ability to translate complex analytical concepts into clear business language.
Strong understanding of data engineering principles and model lifecycle management.
Ability to work across Operations, Engineering, IT, and Data teams.
Strong communication, structured problem solving, and executive-ready storytelling.
Ability to balance analytical rigor with operational practicality.

Nice To Haves

Master’s degree preferred.

Responsibilities

Develop predictive and prescriptive models that support operational forecasting, capacity planning, energy optimization, and reliability analysis.
Identify high-value analytical opportunities across Operations, Engineering, and Customer Experience.
Build scalable machine learning pipelines that integrate with enterprise data platforms.
Evaluate model performance and implement continuous improvement mechanisms.
Integrate analytical models into operational workflows, including maintenance planning, incident response, and capacity forecasting.
Identify opportunities for automation and develop algorithms that streamline manual processes.
Define analytical requirements that inform data engineering, data quality, and data governance priorities.
Partner with Data Engineering to ensure data pipelines support model accuracy and reliability.
Collaborate with Enterprise Architecture to align analytical solutions with long-term technology strategy.
Support reduction of data silos and technical debt through disciplined data integration practices.
Define KPIs and validation frameworks to measure model performance and business impact.
Ensure models adhere to governance standards, including version control, documentation, and reproducibility.
Partner with Operations leadership to ensure analytical outputs reflect real-world operational conditions.
Strengthen the linkage between model performance, operational reliability, and business outcomes.
Handle additional duties as assigned by management.