principal data scientist

At FourKites we have the opportunity to tackle complex challenges with real-world impacts. Whether it’s medical supplies from Cardinal Health or groceries for Walmart, the FourKites platform helps customers operate global supply chains that are efficient, agile and sustainable.

Join a team of curious problem solvers that celebrates differences, leads with empathy and values inclusivity.

We are seeking an exceptional Principal Data Scientist with 15+ years of experience to lead technical innovation in Shipments ETA prediction across multiple transportation modes. This senior individual contributor role requires deep expertise in predictive modeling, supply chain analytics, and transportation logistics, with particular strength in regression problems and modern deep learning architectures. You will be the technical authority driving ETA accuracy improvements for Full Truck Load (FTL), Less-than-Truckload (LTL), Parcel, and complex multi-pickup/delivery scenarios.

What youll be doing

Technical Leadership & Innovation

• ETA Modeling Excellence: Design and implement state-of-the-art predictive models for shipment ETAs across FTL, LTL, Parcel, and multi-stop delivery scenarios
• Cross-Modal Optimization: Develop unified frameworks that account for mode-specific characteristics while maintaining consistency across transportation types
• Complex Routing Intelligence: Build sophisticated models for multi-pickup and delivery scenarios with dynamic routing optimization
• Real-time Prediction Systems: Architect scalable solutions that provide accurate ETAs with sub-second latency for millions of shipments

Advanced Analytics & Research

• Time Series Mastery: Lead development of advanced time series models incorporating seasonality, weather, traffic, and operational constraints
• Geospatial Analytics: Implement cutting-edge location-based models combining GPS tracking, route optimization, and historical patterns
• Feature Engineering Innovation: Create novel features from telematics data, driver behavior, carrier performance, and external data sources
• Uncertainty Quantification: Develop probabilistic models that provide confidence intervals and risk assessments for ETA predictions

Strategic Technical Influence

• Architecture Design: Define the technical roadmap for ETA prediction systems, balancing accuracy, scalability, and operational efficiency
• Cross-Functional Collaboration: Partner with Product, Engineering, and Operations teams to translate business requirements into technical solutions
• Industry Leadership: Represent the company at conferences, publish research, and establish thought leadership in transportation analytics
• Mentorship & Knowledge Transfer: Guide junior data scientists and establish best practices for transportation modeling

Who You are

Education & Experience

• Masters degree in Data Science, Statistics, Computer Science, Mathematics, Operations Research, Industrial Engineering, or related quantitative field (required)
• 15+ years of data science experience with at least 5 years in transportation, logistics, or supply chain analytics
• Deep ETA/Transportation Knowledge: Proven track record of building production ETA systems for multiple transportation modes
• Supply Chain Expertise: Understanding of logistics operations, carrier networks, and transportation economics
• Scalable Systems Experience: Experience with high-volume, real-time prediction systems serving millions of requests

Technical Excellence

Core Data Science Mastery

• Expert-level EDA skills: Advanced proficiency in transportation data analysis, anomaly detection, and pattern recognition
• Advanced Regression Modeling: Deep expertise in time series regression, spatial regression, and hierarchical modeling
• Deep Learning Expertise: Hands-on experience with sequence models, attention mechanisms, and transformer architectures for temporal prediction
• Statistical Modeling: Mastery of Bayesian methods, survival analysis, and probabilistic forecasting

Specialized Transportation Skills

• Geospatial Analytics: Proficiency with PostGIS, spatial indexing, routing algorithms, and map-matching techniques
• Time Series Forecasting: Advanced knowledge of ARIMA, state-space models, neural forecasting (LSTM, GRU, Transformers)
• Optimization Methods: Experience with route optimization, network flow problems, and multi-objective optimization
• Real-time Systems: Understanding of streaming data processing, model serving, and low-latency prediction systems

Technical Infrastructure

• Programming Mastery: Expert-level Python/R with pandas, numpy, scikit-learn, TensorFlow/PyTorch, and transportation-specific libraries
• Big Data Platforms: Experience with Spark, Kafka, and distributed computing for large-scale transportation data
• Database Systems: Advanced SQL skills with time-series databases (InfluxDB, TimescaleDB) and spatial databases
• Cloud & MLOps: Proficiency with cloud platforms (AWS, GCP, Azure), containerization, and ML deployment pipelines

Preferred Qualifications

• Advanced Degree: PhD in Data Science, Statistics, Computer Science, Mathematics, Operations Research, Industrial Engineering, Transportation Engineering, or related quantitative field
• Domain Certifications: Professional certifications in supply chain, logistics, or transportation (APICS, CSCMP, SOLE, etc.)
• Industry Recognition: Publications in transportation/logistics conferences (INFORMS, TRB) or top-tier ML venues
• Leadership Experience: Track record of leading technical initiatives and influencing product strategy
• Open Source Contributions: Contributions to transportation analytics or forecasting libraries

Transportation Domain Challenges Youll Solv

eMulti-Modal ETA Complexit

• yFTL Challenges: Long-haul routing with driver hours-of-service, fuel stops, and carrier-specific performance pattern
• sLTL Complexity: Hub-and-spoke networks with consolidation delays, sorting times, and terminal-specific processin
• gParcel Dynamics: Last-mile delivery optimization with address-level precision and delivery attempt modelin
• gMulti-Stop Scenarios: Complex pickup/delivery sequences with dynamic routing and time window constraint

sAdvanced Technical Problem

• sData Fusion: Integrating GPS tracking, weather data, traffic patterns, carrier performance, and operational constraint
• sUncertainty Modeling: Providing confidence intervals and risk assessments for critical shipment
• sReal-time Adaptation: Updating predictions as new information becomes available during transi
• tPerformance Optimization: Balancing model complexity with sub-second prediction requirement

sWhat You can expect from the rol

• eTechnical Excellence: Access to cutting-edge infrastructure, datasets, and research resource
• sIndustry Impact: Opportunity to shape the future of transportation analytics and supply chain optimizatio
• nProfessional Growth: Conference speaking opportunities, research publication support, and industry networkin
• gInnovation Environment: Collaborative culture with world-class engineering and product team