Data Scientist - Advanced Analytics

Company Information

PACCAR is a Fortune 500 company established in 1905. PACCAR Inc is recognized as a global leader in the commercial vehicle, financial, and customer service fields with internationally recognized brands such as Kenworth, Peterbilt, and DAF trucks. PACCAR is a global technology leader in the design, manufacture and customer support of premium light-, medium- and heavy-duty trucks under the Kenworth, Peterbilt and DAF nameplates and also provides customized financial services, information technology and truck parts related to its principal business.

Whether you want to design the transportation technology of tomorrow, support the staff functions of a dynamic, international leader, or build our excellent products and services, you can develop the career you desire with PACCAR. Get started!
 

Requisition Summary

Join the PACCAR Global Quality team as a Data Scientist, where your role will be central to advancing product reliability through the application of continuous improvements, advanced analytics, and cloud-based solutions. Your work will directly contribute to PACCAR's immediate and strategic future, reinforcing our dedication to setting a high standard within our team. We foster a collaborative workspace that highly values the exchange of knowledge, as well as the infusion of fresh perspectives. Embrace the chance to become an integral part of our dedicated and growing team, where you can shape the future of quality and innovation at PACCAR. This role is based out of the PACCAR Corporate Office in Lewisville, TX. 

This Data Scientist will be tasked with creating, implementing, and sustaining advanced analytics models that assist PACCAR in designing and validating highly effective and reliable products. They will leverage telematics, call center, warranty, test, and production data to unlock decision-making on prognostics and targeted design actions. This role will focus on strategic projects that have a high impact on product quality and customer uptime.

Job Functions / Responsibilities

• Extract, clean, merge, transform and compile data from various data sources, including relational database, flat files, NoSQL databases and unstructured data
• Develop full data science lifecycle projects (from exploratory analysis and hypothesis testing to model deployment and monitoring) with a focus on pragmatic solutions
• Extract signal from data by analyzing correlations, detecting anomalies, performing dimensionality reduction, parsing text, and recommending data quality solutions
• Create materials on data projects, data science architecture and analytics strategies 
• Generate machine learning models that incorporate diverse data types such as text, images, and tabular data into a unified model
• Effectively communicate insights and recommendations derived from data analysis to various stakeholders, including leadership
• Assess the effectiveness and accuracy of new data sources and analytics techniques
• Introduce improvements to increase the speed, accuracy and efficiency of advanced analytics across the organization
• Provide accurate, relevant and meaningful ad-hoc analysis to management to support strategic and tactical decision-making

Qualifications & Skills

Required:

• Bachelor's degree in Data Science or a related field, and 2+ years of applicable job experience

• Deep understanding of statistical techniques, linear algebra, modeling, machine learning and Microsoft Office Suite

• Experience with probability models, synthetic data generation, Command Line Essentials and Git workflow

• Familiarity with deep learning, NLP algorithms, optimization techniques and cloud services especially storage and compute like AWS, Azure or GCP

• Experience designing and implementing AB testing frameworks

• Experience with programming (R, Python) software engineering concepts (OOP, API development) SQL coding, structured and unstructured databases/data warehouses and pipelines (ETL, Machine Learning)

• Proven track record of participating in projects in a highly collaborative, multi-disciplinary team environment

• Ability to define and iterate over minimum viable product, and maintain balance between solid “pragmatism” and “scientific rigor” to meet the needs of a dynamic business

Preferred:

• Master’s degree or PhD in Data Science or related field

• Demonstrate in-depth understanding of data structures

• Experience with container deployments (Docker, Kubernetes, ECS), MLOps including test automation, model retraining and continuous operations of ML systems

• Familiarity with the LLMOps framework for integrating machine learning models into production environments

• Experience working with big data (Scala, Spark)

• Familiarity working in reliability/survival analytics and understanding of Python design patterns

Benefits

As a U.S. PACCAR employee, you have a full range of benefit options including:

• 401k with up to a 5% company match
• Fully funded pension plan that provides monthly benefits after retirement
• Comprehensive paid time off – minimum of 10 paid vacation days (additional days are provided with additional seniority/years of service), 12 paid holidays, and sick time
• Tuition reimbursement for continued education
• Medical, dental, and vision plans for you and your family
• Flexible spending accounts (FSA) and health savings account (HSA)
• Paid short-and long-term disability programs
• Life and accidental death and dismemberment insurance
• EAP services including wellness plans, estate planning, financial counseling and more
• This position is also eligible for a holiday gift.

#LI-CP1