Data Scientist

Bdpinternational•Houston, TX

7d•Onsite

About The Position

The Data Scientist supports the analytical foundation of the BridgeNet 4PL program by transforming large-scale, multi-source supply chain datasets into clean, reliable, and decision-ready information assets. Operating at the intersection of data engineering, statistical modeling, and operational supply chain knowledge, this role owns the end-to-end process of data ingestion, quality assessment, remediation, and pipeline development — ensuring that analytical outputs produced across the program are grounded in well-understood, auditable source data. The Data Scientist works closely with Logistics Supply Chain Engineers, the Logistics Supply Chain Analyst, Control Tower personnel, and external stakeholders including suppliers and LSPs to identify data gaps, implement corrective solutions, and develop predictive models that surface actionable insights across freight, inventory, and supplier performance domains.

Requirements

Bachelor's degree in Data Analytics, Business, Supply Chain, Statistics, or related field.
3–5 years in business analysis, data analysis, or reporting roles within a supply chain, logistics, or professional services environment.
Proficiency in Python or R for data manipulation, statistical analysis, and machine learning model development, with demonstrated experience applying these skills to large, complex, or structurally inconsistent datasets.
Hands-on experience designing and maintaining data pipelines and ETL/ELT workflows, including ingestion from heterogeneous sources such as ERP systems, TMS platforms, EDI feeds, and supplier portals.
Working knowledge of SQL and data querying for pipeline construction, dataset profiling, and data quality validation against consumption layer and data warehouse environments.
Demonstrated ability to identify, classify, and remediate data quality issues — including missing values, structural anomalies, and conflicting data points — using principled, documented methodologies.
Disciplined approach to documentation, including data lineage, transformation logic, model assumptions, and known data limitations.
Understanding of supply chain metrics including OTIF, freight cost analysis, carrier performance, and inventory management KPIs.
Strong attention to detail with demonstrated ability to maintain data accuracy and consistency across multiple reporting products.
Clear written and verbal communication skills with ability to present data findings to non-technical stakeholders.

Nice To Haves

Experience with SAP, Oracle, or comparable ERP data environments.
Background in logistics, freight management, or supply chain operations.
Experience with supply chain management data element mapping.
Experience with data governance practices, including schema documentation, dataset versioning, and calculation methodology standards.
Familiarity with cloud data warehouse platforms (Snowflake, BigQuery, Redshift, or equivalent).
Knowledgeable of inventory management principles, WMS systems, and inventory data landscape.
Excel / Python proficiency for data analysis and automation.
AI Enhanced analytical products and/or workflows

Responsibilities

Ingest, profile, and validate large-scale supply chain datasets sourced from multiple suppliers, LSPs, ERP systems, TMS platforms, and carrier feeds that originate at the consumption layer, establishing a clear baseline of data completeness, accuracy, and structural consistency.
Identify and systematically document data quality issues — including missing elements, erroneous values, structural inconsistencies, and misleading or conflicting data points — and develop root-cause analyses to distinguish systemic data failures from isolated anomalies.
Design and propose data remediation strategies, including gap-filling methodologies, imputation techniques, and cleansing rule sets, then collaborate with internal & external stakeholders to validate and implement solutions.
Monitor and validate incoming supplier and LSP data feeds on an ongoing basis following integration activation, profiling datasets against expected schemas, flagging structural deviations, completeness failures, and value-level anomalies, and escalating confirmed data integrity issues to the integration team with sufficient diagnostic documentation to support root-cause resolution.
Develop and maintain analytical baselines across key value opportunity domains — including freight cost, carrier performance, lead time, and inventory utilization — delivering profiled datasets and baseline calculations in structured, consumable formats to Logistics Supply Chain Engineers and the Logistics Supply Chain Engineering Manager to support project-level baseline development.
Develop and apply statistical and machine learning models to identify patterns, outliers, and predictive signals within supply chain data — including shipment lead times, supplier performance trends, inventory consumption rates, and freight cost anomalies.
Delivery model outputs, predictive findings, and analytical baseline results in structured, consumable formats – including summary tables, annotated datasets, and visualization-ready data packages – enabling the Logistics Supply Chain Analyst to accurately incorporate Data Science outputs into operational dashboards and client reporting products.
Contribute to QBR and MBR reporting packages, in coordination with the Logistics Supply Chain Engineering Manager and Logistics Supply Chain Analyst.
Translate analytical findings into clear, actionable recommendations for operational stakeholders, presenting results in a format accessible to non-technical audiences including Control Tower personnel, Logistics Supply Chain Engineers, and client leadership.
Partner with the Logistics Supply Chain Analyst to ensure data definitions, calculation methodologies, and KPI frameworks are grounded in clean, well-understood source data.
Maintain documentation of data sources, transformation logic, model assumptions, and known data limitations, ensuring analytical outputs are reproducible and auditable.