Looking for a job

David Daniels

@daviddaniels

Senior Data Engineer at VF Corporation who built forecasting pipelines that improved forecast precision by 27.5%.

At VF Corporation, I designed and operated Hadoop and Spark data pipelines for assortment planning, pricing optimization, and supply-chain forecasting. The data lake and processing layer I worked on improved forecast precision by 27.5% and markdown accuracy by 22.8% across North America channels.

I built a real-time demand pipeline with Spark Streaming and Kafka that enabled 40% faster demand response and reduced regional stockouts by 19.3%. I also deployed Spark jobs on Kubernetes and implemented data governance and lineage practices.

Previously, I developed risk monitoring and streaming data platforms at Verisk Analytics, and healthcare analytics and clinical NLP pipelines at Optum. At Blue Yonder, I engineered ingestion and ETL pipelines for annotation datasets supporting computer vision training.

Experience

Work history, roles, and key accomplishments

Current

Senior Data Engineer

Current

VF Corporation

May 2020 - Present (6 years 6 months)

Led enterprise data engineering programs across multi-brand retail portfolios, designing and operating large-scale data pipelines on Hadoop and Spark for assortment planning, pricing optimization, and supply-chain forecasting. Improved forecast precision by 27.5% and markdown accuracy by 22.8%.

Hadoop Spark HDFS Hive HBase Kafka Spark Streaming Airflow Oozie Delta Lake S3 Kubernetes GitHub Actions Terraform Apache Atlas Databricks IAM PII

Senior Data Engineer

Verisk Analytics

Jun 2017 - Mar 2020 (2 years 9 months)

Architected a real-time risk monitoring data platform on AWS processing 200+ live CCTV streams for event detection, alerting, and triage workflows. Built streaming pipelines using Spark Streaming and Kafka, and achieved 85% test coverage with Pytest and Great Expectations.

AWS EMR S3 Kinesis Spark Streaming Kafka Hive Sqoop HBase HDFS Pytest Great Expectations Cloudwatch Prometheus Oozie Airflow HIPAA

AI/ML Engineer

Optum

Sep 2015 - Apr 2017 (1 year 7 months)

Engineered chronic disease risk prediction models using Scikit-learn and TensorFlow, increasing predictive accuracy by ~25%. Designed and deployed FHIR/HL7-compliant APIs with Flask and FastAPI, and built NLP pipelines for clinical notes.

scikit learn TensorFlow Flask fastAPI PySpark Airflow HIPAA Azure ML MLFlow Kubernetes NLP

Data Engineer

Blue Yonder

Jul 2014 - Aug 2015 (1 year 1 month)

Engineered a high-throughput ingestion system for large-scale annotation datasets supporting computer vision training. Built Python-driven ETL pipelines and streamlined data quality assurance through CI/CD automation.

Python ETL CI CD Hadoop HDFS Sqoop Spark