Data Scientist We’re building a universal data API that lets brokers, TMSs, fintechs, and fleets connect to truck and trailer data through a single integration. Catena sits beneath the freight ecosystem, normalizing real-time telematics and execution data so platforms can automate workflows, reduce risk, and make better decisions. As a Data Scientist at Catena, you’ll focus on turning large-scale, messy logistics data into clear insights, proof points, and decision-ready outputs that power product direction, GTM motion, and customer conviction. This is not a research-only or academic role. You’ll work directly with real production data from hundreds of thousands of trucks and trailers and collaborate closely with product, engineering, and go-to-market teams to show what’s possible with Catena’s data layer. Role Summary You’ll own the analysis, exploration, and synthesis of Catena’s data to support three core objectives: - Prove value to TMSs, visibility platforms, brokers, and shippers - Enable GTM with concrete demos, sandboxes, and ROI-driven examples - Inform product strategy with real-world patterns from the network You’ll help create large-scale sandboxes, identify patterns like capacity availability, lane behavior, dwell, and utilization, and translate those into narratives customers can immediately understand. What You’ll Do Insight Generation & Analysis - Analyze large-scale telematics and execution data across fleets, lanes, and time - Identify patterns in capacity, utilization, dwell, reliability, HOS, and asset behavior - Develop metrics and summaries that reflect real-world freight performance GTM Enablement - Build and maintain large-scale sandboxes (1,000+ vehicles) using masked or synthetic data - Create compelling examples for sales, pilots, and customer conversations - Partner with GTM to turn raw data into clear ROI stories and proof points Product & Platform Feedback - Surface data-driven insights that influence roadmap priorities - Validate assumptions about customer use cases with real network data - Help define “decision-grade” metrics that customers actually trust Cross-Functional Collaboration - Work closely with product, engineering, and FDEs to understand data nuances - Support pilots and strategic accounts (e.g., TMS, visibility, broker platforms) - Translate technical findings into clear narratives for non-technical audiences Data Quality & Modeling (Lightweight) - Help define data quality checks, thresholds, and confidence measures - Assist in shaping normalized views (lane history, asset identity, availability) - Focus on interpretability and usability over black-box modeling Skills & Qualifications - Strong analytical foundation with experience in Python, SQL, and data analysis workflows - Comfort working with large, messy, real-world datasets - Ability to reason about operational systems using imperfect data - Experience turning analysis into clear business insights and narratives - Strong communication skills across technical and non-technical teams - Comfortable working in ambiguity and early-stage environments Ideal Candidate Profile - 3–6+ years in data science, analytics, or applied research roles - Experience in logistics, supply chain, marketplaces, or networked platforms is a big plus - Excited about building examples and insight, not just models - Enjoys working close to customers and real business problems - Pragmatic, curious, and impact-driven Why Join Us? - Real Impact: Your work ships to production fast with major freight platforms - Product Influence: FDE insights directly shape the roadmap - Real Scale: Hundreds of thousands of trucks, 130+ telematics providers - High Ownership: No ego, execution-driven culture - Remote-First: Flexible work with optional travel and team meetups - Momentum: Customers use us in production and many are investors Compensation: Competitive salary + meaningful equity, full benefits, 401k match Company Description Catena builds the connectivity infrastructure freight has been missing. We unify telematics, sensors, and operational data into a single API so logistics platforms can automate workflows, reduce fraud, improve safety, and build better products. We’re operators who’ve lived these problems inside carriers, brokerages, TMSs, and financial institutions. We care about accuracy, coverage, and real outcomes not hype. Catena has raised $8.25M from Shaper Capital, Floating Point, Plug and Play, Liquid 2, and leading industry angels.

• Design, build, and operate the Decision Intelligence Engines that power Addi’s personalized customer journeys. • Measure and optimize customer LTV, activation, and retention in real-time. • Design and maintain segmentation models based on behavior, performance, lifecycle stage, and growth potential. • Design, train, and deploy models to predict customer behaviors and risks. • Collaborate with data engineering teams to design and optimize data pipelines that support the seamless deployment of the models into production. • Monitor and evaluate model performance. • Work closely with product managers, marketing teams, and stakeholders to translate data insights into actionable strategies. • Continuously innovate by proposing ML models, algorithms, or tools that enhance customer experience. • Design and execute A/B tests to assess the impact of different offers, product recommendations, and marketing strategies on customer engagement.

• Partner with our Product and Business Teams to understand their needs, translate them into data science solutions, and provide actionable insights. • Develop and implement advanced data science solutions (including ML models, AI products, optimization frameworks etc.). • Collaborate closely with cross-functional teams to ensure seamless integration of data-driven initiatives. • Stay ahead of the curve exploring cutting-edge methods and being on top of new trends in Data Science & AI. • Communicate insights and recommendations to the management and business teams, and other data community members.

• Develop and productionize statistical machine learning models for probabilistic country attribution based on browsing patterns and behavioral signals • Design and refine predictive models and statistical algorithms to improve accuracy and reliability of behavioral calculations • Work with petabyte-scale datasets to extract, clean, and analyze large volumes of behavioral data • Build scalable data pipelines and modeling workflows using Python and SQL • Collaborate with engineering and product teams to integrate models into production services • Create clear visualizations and reports to communicate model performance and insights • Own end-to-end algorithm development and model lifecycle management • Mentor junior team members as the role evolves into Data Scientist Lead