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.

Job Description

The Cat® Digital group is the digital and technology arm of Caterpillar Inc., responsible for delivering world-class digital capabilities across our products and services. With more than 1.5 million connected assets globally, Cat Digital leverages data, advanced analytics, and AI to help customers build a better, more sustainable world.

Job Summary

eCommerce is a key digital enabler in Caterpillar’s aftermarket parts and services growth strategy. The Senior Data Scientist – Search plays a critical hands-on role in designing, building, and deploying advanced AI/ML and search relevance models that power scalable, high-quality enterprise search experiences.

This role focuses on end-to-end model development, experimentation, and optimization for search and discovery, working closely with product, engineering, and platform teams to improve relevance, personalization, and business outcomes.

What You Will Do

Search Model Development & Optimization

• Design, develop, and deploy ML, deep learning, and relevance models for enterprise search, including ranking, retrieval, and semantic search

• Implement and fine-tune Learning-to-Rank models (e.g., LambdaMART, deep ranking models) to improve result relevance and user satisfaction

• Optimize search pipelines using keyword, behavioral, contextual, and semantic signals

AI, NLP, and Generative Search

• Build and enhance NLP-driven capabilities such as query understanding, intent detection, and query rewriting

• Apply Generative AI and LLM techniques including fine-tuning, prompt engineering, and Retrieval-Augmented Generation (RAG) for search use cases

• Work with retrieval methods such as BM25, semantic retrieval, and vector search

Behavioral, Contextual, and Personalization Models

• Develop behavioural models leveraging user signals, clickstream data, and search interactions

• Build contextual intent models to improve categorization and relevance

• Implement personalization models, including rule-based segmentation, ML-based recommendations, and implicit personalization

Data Analysis & Experimentation

• Analyze large-scale search logs and product data to identify relevance gaps and improvement opportunities

• Define and track search KPIs (CTR, zero-result searches, query distribution, relevance metrics)

• Design and execute A/B tests to validate model and feature improvements (nice to have)

MLOps & Platform Collaboration

• Build robust feature engineering, labeling, and model pipelines

• Deploy and monitor models using MLOps frameworks and cloud-native platforms (AWS, Azure, or GCP)

• Collaborate with engineering teams to operationalize models through APIs and scalable services

Cross-Functional Collaboration

• Partner with product managers, engineers, and data science peers to align search capabilities with business objectives

• Contribute technical insights, documentation, and recommendations to influence product and platform decisions

What You Will Have

Core Technical Skills

• Strong experience developing and deploying ML models for search, recommendation, or relevance-driven systems

• Hands-on expertise with Python and data science libraries (NumPy, pandas, SciPy, etc.)

• Solid understanding of machine learning techniques including ranking, clustering, regression, and neural networks

• Experience working with large-scale datasets, search logs, and production ML systems

AI / ML & Search Experience

• Practical experience with search relevance techniques such as Learning-to-Rank, semantic retrieval, and NLP

• Exposure to Generative AI and LLM-based search solutions (RAG, prompt engineering, embeddings)

• Familiarity with personalization and recommendation systems

Platform & Cloud

• Experience deploying models through ML platforms, APIs, and cloud environments (AWS, Azure, or GCP)

• Working knowledge of version control systems (Git/GitHub)

• Experience operating in Agile delivery environments

Analytical & Business Acumen

• Strong statistical knowledge to translate business problems into measurable analytics solutions

• Ability to analyze results, identify root causes, and recommend data-driven improvements

• Effective communication skills to explain complex models and insights to technical and non-technical stakeholders

Considerations for Top Candidates

• Bachelor’s or Master’s degree (or PhD) in Data Science, Statistics, Computer Science, Engineering, Mathematics, or equivalent technical field

• Typically 5+ years of experience in applied data science, machine learning, or search-related systems

• Experience with industrial, manufacturing, automotive, or large-scale enterprise datasets is a strong plus

• Familiarity with heavy equipment engineering data or eCommerce search domains is beneficial

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.