Lead Data Scientist

Caterpillar•San Diego, CA

17d•Onsite

About The Position

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. Lead Data Scientist – Power the future with AI and Digital Twins At Solar Turbines, we’re driving smarter decisions through data science and physics—and we’re looking for a Lead Data Scientist to help us push boundaries. In this role, you’ll interact with massive datasets, apply advanced machine learning and physics methods in Python and Matlab, and work on a team to develop core AI products that help our customers achieve industry leading reliability, performance and growth.

Requirements

Machine Learning: Experience applying ML algorithms and techniques to solve both physics and/or business problems.
Proficient in Python, with knowledge of libraries like pandas, NumPy, SciPy, Scikit-learn, PyTorch, and SpaCy.
Statistical Analysis & Modeling: Solid understanding of hypothesis testing, and predictive modeling. Able to validate models using standard statistical measures and interpret results.
Physics & Engineering: Solid understanding of the physics of 1D heat transfer and fluid mechanics with ability to solve these types of problems using python or Matlab libraries.
Data Handling: Ability to write SQL statements for database access using SQL Alchemy and CX Oracle. Able to write and optimize queries across multiple tables and schemas.
Programming & Automation: Comfortable developing scripts and tools to automate digital twin workflows. Ability to use LLMs for code creation but familiar with structured programming practices and debugging techniques to ensure output is correct.
Visualization & Communication: Excellent communication and visualization skills. Need to feel comfortable creating presentations that make technical concepts easy for non-technical audience members to understand.
Analytical & Business Acumen Analytical Thinking Above average problem-solving and critical thinking. Ability to take loosely defined requirements or statements of value and turn them into a structured problem that can be solved mathematically. Capable of comparing alternative solutions and making optimal decisions.
Master of Science (MS) in Mechanical Engineering, Chemical Engineering, Applied Mathematics, or Physics is required, PhD preferred.

Nice To Haves

At least 2 years of experience post education in mechanical engineering roles.
Many years of experience in engineering analysis, including structural, thermal, fluid, and/or performance calculations for the purposes modeling and simulation.
Many years of experience modeling physical systems starting with first principles equations and implementing ODEs or PDEs in Matlab, Python or similar programming languages.
Some experience with control theory and applications to dynamic systems and industrial machines.
Published technical papers at conferences or journals in the engineering and/or physics fields

Responsibilities

Lead data mining, modeling, and analysis of time series data, event data and meta data to build anomaly detection models to be used within InSight Platform.
Apply machine learning and physics principles to create, explore and validate hybrid digital twin models using lumped parameter ODE models, PINNs and NeuralODEs to approximate PDE model outputs.
Design and optimize algorithms to improve accuracy, numerical performance, and scalability.
Build compelling visualizations and present findings to stakeholders using tools like Quicksight or Plotly.
Collaborate across teams and business segments to define analytical requirements and deliver actionable solutions related to InSight Platform’s digital twin strategy.
Work with stakeholders, SMEs and customers to develop project plans and execution schedules.