• Develop and maintain capacity models for compute, storage, and network infrastructure across global environments. • Build and productionize advanced time‑series forecasts (e.g., ARIMA/ETS, Prophet, XGBoost/LightGBM) to predict demand, saturation points, and runway. • Conduct scenario modeling (“what‑if”) on deployment plans, workload changes, demand spikes, and hardware refresh strategies. • Analyze historical utilization to identify emerging risks, inefficiencies, and optimization opportunities. • Design, build, and maintain Python‑based data pipelines for ingesting, transforming, and validating large‑scale infrastructure telemetry. • Create ETL/ELT workflows to support analytics, modeling, and reporting. • Integrate data from observability platforms (e.g., Prometheus/Grafana), CMDB/asset systems, and internal services. • Develop APIs/services to expose forecast results and capacity signals to dashboards and tooling. • Build executive‑ready dashboards in Power BI (DAX, Power Query, custom visuals) and integrate real‑time forecasting outputs. • Deliver clear, compelling insights to engineering, operations, and finance leaders to support both strategic and tactical decision‑making. • Automate reporting workflows and ensure up‑to‑date visibility into runway, utilization, and risk posture. • Partner with engineering, operations, and finance teams to align capacity plans with growth, reliability, and cost objectives. • Establish standards for model governance, documentation, and data quality. • Drive continuous improvement of capacity planning systems, tooling, and analytics frameworks.

• Collaborate with engineers, product teams and analysts to develop data products that are precise and insightful. • Own the data product lifecycle, including designing tracking plans, developing data models, ELT pipelines, and self-serve data products. • Design and maintain an AI-enabled semantic layer that allows business users to interact with data through natural language using agentic AI tools. • Find creative ways to integrate AI into the Data lifecycle. • Be the data steward, ensuring data quality and consistent metrics.

• Build machine-learning systems that power some of the most advanced logistics intelligence products in the industry • Analyze large, noisy datasets from cameras, OCR, detections, and geospatial pipelines to uncover actionable patterns • Design and evaluate algorithms for truck re-identification, geospatial clustering, equipment classification, OCR text labeling, anomaly detection, and more • Collaborate with engineering and data engineering teams to scale models from prototype to production • Work closely with product teams to deeply understand customer needs and translate them into modeling and analytics initiatives • Apply scientific thinking to continuously test, iterate, and refine approaches as new data becomes available

• Develop and maintain data replication and ELT pipelines feeding the analytics platform • Design and implement dimensional data models using star and snowflake schemas • Build and maintain data transformations that convert operational data into analytics-ready datasets • Implement data quality checks, testing, and validation to ensure accuracy of KPIs and metrics • Create and maintain documentation for data models, business logic, and data lineage • Establish data governance standards for analytics, including naming conventions, access controls, and metric definitions • Partner with BI tool users (Tableau, Looker, Power BI) to design efficient, performant data structures • Mentor junior engineers and analysts on data modeling, SQL optimization, and analytics best practices