Principal Machine Learning Scientist

Job Title: Principal Data Scientist, Vehicle Analytics

Company Overview

Diesel Laptops is a leading provider of diagnostic tools, repair information, software, training, and technology solutions for the commercial truck and off-highway vehicle repair industry. We help repair facilities, fleets, technicians, and industry partners reduce downtime, improve repair accuracy, and make better operational decisions.

We are seeking a Principal Data Scientist, Vehicle Analytics, to help transform large volumes of vehicle telemetry, service history, repair outcomes, and operational data into meaningful insights, predictive capabilities, and production-ready analytical solutions.

Position Summary

The Principal Data Scientist, Vehicle Analytics, is a senior individual contributor responsible for solving complex business, vehicle, and engineering problems through statistical analysis, experimentation, predictive modeling, and applied data science.

This role partners closely with Software Engineering, Data Engineering, Product, Remote Solutions Engineering, and customer-facing teams to identify high-value problems, define analytical approaches, validate hypotheses, and deploy reliable data-driven capabilities.

Machine learning is an important part of the role, but success is defined by selecting the most appropriate analytical method for each problem rather than applying machine learning where a simpler statistical or analytical approach would be more reliable, explainable, or useful.

This position does not have routine direct reports but is expected to provide scientific leadership, technical mentorship, and guidance across the organization.

Key Responsibilities

Data Analysis and Scientific Problem Solving

• Investigate complex business, vehicle, and engineering problems using exploratory data analysis, statistical analysis, experimentation, and hypothesis testing.
• Analyze vehicle telemetry, time-series data, fault codes, service history, repair outcomes, and operational data.
• Translate ambiguous customer and business questions into measurable hypotheses, analytical plans, and actionable recommendations.
• Identify trends, anomalies, failure patterns, and operational drivers that affect vehicle reliability, maintenance, and customer outcomes.
• Present findings, limitations, uncertainty, and recommendations to technical and nontechnical stakeholders.

Statistical Modeling and Machine Learning

• Design, develop, validate, and improve statistical models, anomaly-detection methods, predictive-maintenance models, classification systems, and related analytical solutions.
• Determine whether statistical analysis, machine learning, experimentation, or another analytical method is most appropriate for the problem.
• Define and monitor performance measures such as precision, recall, F1 score, false-positive rate, stability, latency, and business impact.
• Document assumptions, methodology, validation results, limitations, and performance findings to ensure reproducibility and transparency.
• Monitor deployed models and analyses and recommend retraining, redesign, or retirement when appropriate.

Data Products and Production Systems

• Build production-ready analytical workflows, contextual tools, reports, prototypes, and model components.
• Partner with Data Engineering and Software Engineering to productionize analyses and models using reliable pipelines, APIs, testing, observability, and deployment practices.
• Contribute code and technical documentation using approved engineering standards.
• Support testing, validation, monitoring, and continuous improvement of production data-science solutions.
• Ensure analytical work is auditable, reproducible, maintainable, and appropriately documented.

Collaboration and Technical Leadership

• Partner with Product, Engineering, Remote Solutions Engineering, Customer Success, and business leaders to identify and prioritize analytical opportunities.
• Participate in technical design discussions, scientific reviews, code reviews, and model-validation reviews.
• Mentor data scientists, analysts, and engineers in statistics, experimentation, analytical reasoning, and model evaluation.
• Establish and promote best practices for analytical quality, reproducibility, documentation, and responsible model use.
• Communicate scientific findings and recommendations to executives, customers, and other stakeholders when required.

Qualifications

Required Qualifications

• Master’s degree in Data Science, Statistics, Computer Science, Applied Mathematics, Engineering, or a related quantitative field, or equivalent advanced professional experience.
• Seven or more years of progressive experience in applied data science, statistical modeling, machine learning, or quantitative research.
• Demonstrated experience solving complex problems using large, imperfect, high-volume, or time-series datasets.
• Advanced proficiency with Python and SQL.
• Strong experience with Pandas, NumPy, SciPy, and Jupyter.
• Strong foundation in statistics, experimental design, hypothesis testing, model validation, and communication of uncertainty.
• Experience developing and deploying production data-science or machine-learning solutions.
• Ability to independently define methodology, evaluate technical tradeoffs, and lead complex analytical initiatives.
• Strong written and verbal communication skills.

Preferred Qualifications

• PhD in Data Science, Statistics, Computer Science, Applied Mathematics, Engineering, or a related quantitative field.
• Experience with vehicle telemetry, IoT, connected-device, fleet, transportation, predictive-maintenance, or industrial time-series data.
• Experience with anomaly detection, equipment-failure prediction, maintenance optimization, natural-language processing, or large language models.
• Experience with dbt, Dagster, Apache Flink, ClickHouse, PostgreSQL, Apache Iceberg, Docker, and MLflow.
• Experience producing statistically valid customer-facing analyses, technical case studies, or research reports.
• Publication, patent, or significant applied-research experience.

Core Technologies

• Python
• SQL
• Pandas
• NumPy
• SciPy
• Jupyter Notebooks
• dbt
• Dagster
• Apache Flink
• ClickHouse
• PostgreSQL
• Apache Iceberg
• Git
• GitHub
• Docker
• MLflow

Position Details

• Full-time
• Exempt
• Principal individual-contributor role
• Remote within the United States, with hybrid eligibility in Columbia, South Carolina
• Occasional travel may be required