JOB DESCRIPTION

Description

The Cat® Digital group is the digital and 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 IoT and other data, advanced analytics, and ML/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. 

Cat Digital’s IoT Analytics team is looking for a talented and motivated Lead Data Scientist to develop and deliver ML/AI-based analytics models to support condition monitoring for customers and dealers, as well as improve product development for the enterprise. As a Lead Data Scientist, you will use machine learning, deep learning, neural networks, and other analytics techniques on time-series machine sensor data and other datasets to better understand data patterns, identify device health anomalies, predict equipment failure modes, etc.

The Lead Data Scientist is recognized as a technical leader within the company and is becoming recognized outside the company for their analytics expertise.  Approximately 75% of this role focuses on direct execution as an expert technical contributor, with 25% consisting of coaching and mentoring junior data scientists and giving technical leadership to multiple concurrent projects. The incumbent will be expected to frame problems, identify/create/explore alternatives, and formulate/negotiate/develop/validate solutions. He/she must be a fast learner and possess excellent communication skills to effectively collaborate with diverse teams (including other data scientists, product design/simulation experts, software/application developers, condition monitoring analysts) to develop analytics algorithms that deliver customer value on complex IoT systems. Decisions may affect the project or program team, the division or business unit, internal and external customers and the market, and may require justification to upper management.

Example projects include:

·         Applying machine learning to timeseries datasets to classify machine failure modes

·         Improving machine health monitoring capability via digital twin development

·         Developing new anomaly detection schemes

·         Exploring new analytic techniques to improve issue detection accuracy and reduce false positives

Qualifications