Grant B. Kepley
Data Engineer, Agricultural technology
Sacramento, CA · (916) 555 0129 · name@example.com · linkedin.com/in/grantbkepley
Key Qualifications
EXPERIENCE
Seven years in data engineering, four of them supporting machine learning teams.
INDUSTRIES
Agricultural technology, irrigation services, food processing.
SPECIALTIES
Feature stores, pipeline design, orchestration, data contracts.
SYSTEMS
Databricks, Spark, Airflow, dbt, Snowflake, MLflow, Python.
CREDENTIALS
Databricks Certified Data Engineer Professional.
EDUCATION
Bachelor of Science in computer science, University of California Davis.
Executive Summary
Data engineer inside the data science and artificial intelligence group at an agricultural technology company. Seven years building the pipelines and the feature store that six data scientists train yield models on. Owns ingestion from field sensors and grower records through to the features that reach production scoring.
Signature Achievements
- Built the feature store that ended six months of scientists writing the same soil moisture feature four different ways.
- Cut training data preparation for the yield model from nine hours to 35 minutes by rewriting three Spark jobs.
- Reduced Databricks compute spend by 27 percent through cluster right sizing and by killing 40 abandoned notebooks jobs.
- Closed the gap between training and serving features, which removed a 4 point accuracy drop nobody could explain.
- Wrote data contracts with the device team so a sensor firmware change stopped silently breaking the nightly load.
Professional Experience
Data Engineer
Verde Fields Agronomics, Sacramento, CA 2022 to present
One of three engineers in a 14 person data science and artificial intelligence group serving 3,000 grower accounts.
- Owns the Spark and Airflow pipelines that land field sensor, weather and grower record data into Databricks each night.
- Runs the feature store and the model registry in MLflow that six data scientists depend on.
- Maintains the batch scoring pipeline that writes yield and irrigation recommendations back to the grower application.
- Publishes freshness and volume checks so the science team learns about a bad feed before a model does.
Data Engineer
Delta Valley Food Processing, Stockton, CA 2019 to 2022
Two person data team supporting operations and quality at four processing plants.
- Built the first warehouse the company had, modeling production and quality data in dbt on Snowflake.
- Replaced 30 scheduled scripts with orchestrated Airflow pipelines and real alerting.
- Supported the food safety team with traceability queries during two customer audits.
Licensure and Certification
Databricks Certified Data Engineer Professional, 2023
Education
Bachelor of Science in computer science, University of California Davis, 2019
Core Skills
Python · Spark · Databricks · Airflow · dbt · Snowflake · MLflow · Feature stores · Data contracts · Structured Query Language