Data Scientist (2008)

About Kooner Fleet Management Solutions 

Kooner Fleet Management Solutions is one of the fastest-growing national providers of on-site fleet maintenance, preventative service, and mobile repair solutions. With nearly a decade of industry experience, Kooner FMS helps fleets reduce downtime, extend vehicle life, and simplify operations through proactive maintenance programs and advanced technology. 

As a family-founded and field-first company, we take pride in delivering trusted partnerships, exceptional service, and innovative fleet management solutions that keep America’s trucks and trailers road-ready. 

About the Data Scientist Role 

We are looking for a Data Scientist to serve as our in-house analytical authority, reporting directly to the CFO, embedded with the executive team, and working across every department to surface the insights that drive how we run and grow the business. 

This is not a reporting role. This person builds the infrastructure and intelligence layer between our data systems and our decision-making. They don't just find trends, they architect the pipelines, models, and systems that make those trends visible at scale. They find the money we are leaving on the table, identify where we are operating inefficiently, and deliver clear recommendations backed by rigorous statistical modeling – not just charts.  

This is a hybrid opportunity based out of our corporate office in Sacramento, CA.

Where You’ll Make an Impact 

• Connect and analyze data across FleetIQ, Samsara GPS, Rippling, time schedules, QuickBooks, and Power BI to build a unified view of business performance 

• Identify cost-saving opportunities and operational inefficiencies across departments; workforce, fleet, dispatch, finance, and field operations 

• Develop and maintain dashboards and scorecards in Power BI and Tableau that give leadership and department heads real-time visibility into KPIs 

• Analyze technician profitability, labor cost vs. output, overtime patterns, and timecard compliance 

• Evaluate GPS and fleet data against clock records to detect off-clock vehicle use, idle time, and route inefficiency 

• Assess dispatch metrics - time to first assignment, technician response times, job completion rates - and identify structural improvements 

• Leverage AI tools and prompt engineering to accelerate analysis, automate summaries, and enhance the depth of insight from existing data 

• Build and maintain master mapping tables to normalize technician names, truck assignments, territory codes, and cross-system identifiers 

• Partner with the CFO and executive team to frame business questions analytically and return with data-backed recommendations 

• Proactively surface trends, anomalies, and risks the business is not yet measuring before they become problems 

What a Strong Performance Looks Like 

• 60 days: You have audited all key data sources, mapped their schemas and relationships, stood up a data warehouse environment, and delivered a first cross-department performance view to the CFO. 
• 6 months: Automated data pipelines are running in production. Dashboards are self-refreshing. You have identified and quantified at least three material cost-saving or efficiency opportunities with model-backed recommended actions. 
• 12 months: A production ML model is influencing at least one operational process. Data is embedded in how the company makes decisions. Leaders are citing your analyses in operational and financial planning. 

What Makes You a Great Fit 

Required Experience 

• 8–10 years minimum in data science, data engineering, or a senior analytical role with a strong engineering component 
• Bachelor's degree in Computer Science, Statistics, Mathematics, Data Science, or related quantitative field required; Master's degree preferred 
• Background in field service, logistics, last-mile delivery, fleet operations, or a similarly data-rich operational business strongly preferred 
• Demonstrated history of translating data findings into business decisions, not just reports 
• Experience working directly with finance leadership or C-suite as an analytical partner 
• Proven ability to integrate data across multiple enterprise platforms with inconsistent formats and naming conventions 

Technical Skills 

• Expert-level SQL – complex joins, window functions, CTEs, query optimization, and working with multi-source messy data at scale 
• Python at a production level – not just pandas scripts, but well-struc