Data Scientist

Career Area:

Job Description:

Your Work Shapes the World at Caterpillar Inc.

When you join Caterpillar, you're joining a global team who cares not just about the work we do – but also about each other. We are the makers, problem solvers, and future world builders who are creating stronger, more sustainable communities. We don't just talk about progress and innovation here – we make it happen, with our customers, where we work and live. Together, we are building a better world, so we can all enjoy living in it.

Cat Digital is the digital and technology arm of Caterpillar Inc., responsible for bringing world class digital capabilities to our products and services. With almost one million connected assets worldwide, we're focused on using IoT and other data, technology, advanced analytics and AI capabilities to help our customers build a better world.

Build the Digital Backbone of Modern Manufacturing

We’re assembling a dynamic team to develop and scale our Manufacturing & Supply Digital Platform—a next-generation software framework that transforms how manufacturing and supply operations connect, collaborate, and optimize.

This platform is not an ERP system. It’s a purpose-built digital layer that integrates data, processes, and resources across the entire manufacturing lifecycle—from design and engineering to production and distribution.

This initiative is powered by NVIDIA technologies, including the Omniverse platform and AI computing capabilities, enabling immersive digital twins, accelerated simulation, and intelligent automation. You’ll be part of a team that’s not just building software—but shaping the future of how manufacturing works through AI-driven, collaborative, and scalable digital solutions.

As part of this initiative, you’ll contribute to:

• System Integration: Seamlessly connecting diverse manufacturing and supply systems, data sources, and workflows into a unified digital ecosystem.
• Data-Driven Decision Making: Harnessing real-time data collection, analysis, and visualization to deliver actionable insights and operational intelligence.
• Automation & Optimization: Driving efficiency through intelligent scheduling, predictive maintenance, and quality control—without replacing core transactional systems.
• Enhanced Collaboration: Enabling transparent communication and coordination across teams, functions, and geographies.

If you're passionate about digital platforms, industrial innovation, and working with cutting-edge technologies, this is your opportunity to make a meaningful impact.

Key Responsibilities:

• Collect, preprocess and analyze multi-modal manufacturing datasets: sensor logs, event streams, image/video from virtual and real factory environments.
• Build and tune supervised/unsupervised models for predictive yield analytics, process bottleneck detection, and machine/production asset health forecasting.
• Design, generate, and validate synthetic data flows via OpenUSD-based digital twins for enhanced model robustness and continuous learning.
• Optimize model features through data augmentation, outlier filtering, and dimensionality reduction (PCA, t-SNE etc.).
• Collaborate with the design of metric dashboards (e.g., FID, Inception Score) for monitoring generative model performance.

Required Skills:

• Expert in Python (pandas, NumPy, SciPy, scikitlearn, PyTorch ecosystem); writes clean, testable code and optimizes when performance matters.
• Strong background in machine learning, with hands-on depth in PyTorch plus solid grasp of classical methods (tree based models, clustering, timeseries, anomaly detection) to choose the right approach for the problem.
• Basic optimization know-how (gradient descent, evolutionary, reinforcement learning for scheduling/planning).

Nice to Have Skills:

• Experience with USD asset manipulation, data ingestion from Omniverse simulations & digital twin development expertise.
• Data pipeline development (ETL, Airflow, Kafka).
• Cloud tools for scalable ML (AWS/GCP with containerized workloads).
• Understanding of domains across plant/line telemetry, quality, maintenance, logistics, or scheduling—can translate noisy signals into predictive and prescriptive use cases

Educational Background: Typically requires a Bachelor’s degree, preferably in computer science, Artificial Intelligence, Data Science, mathematics, or a similar field with quantitative coursework, and 4-5 years of professional experience in associated field is required, a Master’s degree and 2-3 years of experience, or a PhD in one of the associated fields.

Posting Dates:

Caterpillar is an Equal Opportunity Employer. Qualified applicants of any age are encouraged to apply

Not ready to apply? Join our Talent Community.