Lead Data Scientist - Digital Elevator Solutions

TK Elevator is currently seeking a Lead Data Scientist
- Digital Elevator Solutions in Atlanta, GA
.

The Lead Data Scientist
- Digital Elevator Solutions will play a critical role within TK Elevator’s North America Digital Operations Center (DOC), transforming IoT, service, and operational data into advanced analytics and AI-driven solutions that improve equipment reliability, field productivity, service delivery, and customer outcomes. This role combines deep, hands‑on data science expertise with technical leadership and strong business acumen. The Lead Data Scientist will lead the development and deployment of machine learning, predictive analytics, and AI solutions using data from connected elevators and escalators, including equipment movements, sensor data, error codes, service history, and other operational information.

The successful candidate will work closely with Field Operations, Engineering, Product Management, R&D, Data Engineering, and Digital teams to identify operational challenges and translate them into scalable, data‑driven solutions with measurable business value.

As part of a global Digital Operations Center network, this role will also collaborate extensively with data science, engineering, and digital counterparts across multiple global locations. The Lead Data Scientist will help leverage solutions and best practices developed globally while identifying opportunities to scale successful North American innovations across the broader organization.

The ideal candidate is equally comfortable developing models in Python, exploring complex datasets in SQL and Databricks, collaborating with technical teams, discussing operational challenges with field leaders, and communicating results and business impact to senior stakeholders.

• Lead the design, development, deployment, and ongoing optimization of machine learning models, predictive analytics, and AI solutions supporting connected elevator and escalator technologies.
• Analyze IoT sensor streams, equipment movements, error codes, service history, and other operational data to predict service needs and potential equipment failures before breakdowns occur.
• Develop predictive maintenance, anomaly detection, classification, regression, and time‑series forecasting models that improve equipment reliability, uptime, and serviceability.
• Analyze large and complex datasets to identify trends, patterns, anomalies, and opportunities to improve field productivity, service quality, and customer outcomes.
• Translate operational and business challenges into scalable analytical solutions with clearly defined success metrics and measurable business impact.
• Manage and contribute to the full machine learning lifecycle, from data exploration and model development through validation, deployment, monitoring, and continuous improvement.

• Drive the development and advancement of data-driven digital capabilities, including:
  • Predictive maintenance
  • Remote monitoring and diagnostics
  • AI-driven fault detection
  • Equipment performance and reliability analytics
  • Field service optimization
  • Connected equipment solutions
  • Customer and equipment insights
  • Digital twin and other emerging connected technologies
• Develop solutions that provide field technicians with relevant, contextual equipment and service information before, during, and after maintenance activities.
• Partner with Field Operations, Product Management, Engineering, and R&D teams to identify high‑value use cases and develop solutions that address real‑world service and equipment challenges.
• Support the development of analytics, insights, and tools that improve decision‑making for field teams, operational leaders, and customers.

• Develop and implement AI and machine learning solutions utilizing techniques such as:
  • Time‑series forecasting
  • Anomaly detection
  • Classification and regression
  • Predictive analytics
  • Statistical modeling
  • Natural language processing
  • Generative AI and large language models
  • Deep learning techniques, where appropriate
• Develop and refine prompts, context, data inputs, and supporting frameworks for…