Caterpillar Data Scientist I, Cat Digital

  • Full Time
Posted: 7.16.21

Caterpillar Data Scientist I, Cat Digital


The Cat® Digital group is the digital technology arm of Caterpillar Inc., responsible for bringing world class capabilities to our products and services. With almost one million connected assets worldwide, we’re focused on using data, advanced analytics, and AI capabilities to help our customers build a better world. To accomplish this, we’re deploying analytics that generate insights, recommend optimized decisions, and improve products by intelligently integrating massive quantities of telematics information, transactional records, images, unstructured documents, and other data sources. Join our group of world-class data scientists and apply machine learning to remote sensor data to diagnose potential issues and schedule proactive repairs before failures arise. Or improve products and product recommendations by developing a detailed understanding of how customers use their Cat equipment. The opportunity to make an impact is remarkable!

The AI-Based Modeling Team within Cat Digital’s Advanced IoT Analytics organization is looking for a talented and motivated Data Scientist Ito develop condition monitoring and anomaly detection models to power asset management solutions for customers and dealers. You will use machine learning, deep learning, and statistics-based/physics-based analytics techniques on time-series sensor data, machine fault codes, inspections and analysis records, and other datasets to identify health anomalies, predict equipment failure modes, estimate remaining useful life, and build equipment risk models. Excellent python coding skills are paramount, but familiarity with modeling and analysis of heavy equipment engineering systems is a plus.


Caterpillar uses quantitative techniques to solve problems.  Typical problems include maximizing OPACC through improvements in Inventory Costs, Material Costs, NPI costs, etc; determining the principal drivers of health care costs; recommending the optimal supplier for a part; identifying sales, rental, and service opportunities for Caterpillar dealers; and developing simulation/optimization capabilities to model a new facility or product feature. In addition, analytics experts also provide assistance to high-profile enterprise-wide projects such as the Engineered Value Chain.

The key role of this second level analyst position is to move from learning and assisting others to learning to contribute independently.  The Data Scientist I is expected to be familiar with the company’s processes, products, and organization. Work is typically directed by a project or team lead who might review both methods and results. Decisions on routine, limited risk issues that may affect the project team, suppliers or internal customers may be made by this position. Challenges include meeting expectations in delivering results, learning to consider alternative courses of actions, making timely decisions and developing communication skills.

Individuals in this position might expect to have several assignments allowing them to gain experience on multiple projects. They will be expected to apply theory and concept in contributing to the solution in the assigned area.

The job function may include data collection and analysis; development, validation, application, and refinement of statistical models; application of related digital technologies in processing both the inputs and outputs from the models.

The Data Scientist I demonstrates an expanded breadth of knowledge and the ability to handle basic issues independently. The incumbent demonstrates very good communication skills; above average planning and organization, teamwork, and decision-making skills; a strong concern for customers; and has basic knowledge of Caterpillar Inc., and its products and services.

Example projects include:

  • Applying machine learning/deep learning to remote sensor data to diagnose potential issues and recommend proactive repairs before failure
  • Developing machine anomaly detection capabilities


  • B.S. in data science, computer science, applied mathematics/statistics, physics, electrical, mechanical or industrial engineering
  • 2-3 years of work experience (or M.S. plus 0-1 years)
  • Strong python skills for data science (numpy, pandas, pyspark, pytorch, keras)


  • Demonstrated expertise applying machine learning / deep learning to telematics data
  • Familiarity with modeling and analysis of heavy equipment systems (machine, engine, transmission, etc.)
  • AWS Cloud Practitioner certification (or other advanced AWS certification)
  • Experience deploying production code on AWS in an Agile software development environment
  • Excellent presentation, communication, interpersonal, and collaboration skills
  • Demonstrated capability to take initiative and lead in the presence of ambiguity to deliver innovative solutions

Relocation is available for this position. Visa sponsorship available for eligible applicants.

EEO/AA Employer.  All qualified individuals – Including minorities, females, veterans and individuals with disabilities – are encouraged to apply.

Click here to apply!