Nick Bohall

About Nick Bohall

Data Scientist with 5+ years building production machine learning systems and data infrastructure. I specialize in the intersection of ML and platform engineering - developing automated pipelines, distributed data processing systems, and tooling that enables rapid model development and deployment at scale.What I build: • ML infrastructure: Model management APIs, automated deployment pipelines, A/B testing frameworks • Distributed systems: Spark/Scala data processing handling billions of records • Production tooling: RESTful APIs, orchestration systems, ensemble model frameworks • Data platforms: ETL pipelines, feature engineering infrastructure, model monitoringTechnical foundation: • Languages: Python, SQL, Scala, TypeScript, R, Bash • ML/Data: Scikit-learn, TensorFlow, Keras, Pandas, PySpark, Spark SQL • Infrastructure: Apache Spark, HDFS, Airflow, Docker, Linux, MariaDB • Cloud & Tools: AWS, Git, Protocol Buffers, RESTful APIsI\'ve shipped ML models generating $15M+ in projected revenue while building the infrastructure that makes rapid experimentation and deployment possible. Currently focused on expanding my expertise in orchestration, cloud platforms, and MLOps to build world-class ML systems.

Experience

1. Data Scientist - Ml Infrastructure Focus

   Wiland

   Jul 2024 — Present

   Building ML platform infrastructure and production systems that enable rapid model development and deployment:ML Platform & Infrastructure: • Architected model management infrastructure using TypeScript APIs and Protocol Buffers, enabling automated tracking and deployment of production models across pipelines • Built automated ML framework with scikit-learn featuring dynamic model selection, hyperparameter tuning, and A/B backtesting capabilities (projected $2M revenue impact) • Developed ensemble model infrastructure with automated normalization, null handling, outlier detection, and quality validation for production scoring systems • Implemented comprehensive logging, testing, and documentation standards across all ML systemsDistributed Data Engineering: • Engineered Spark/Scala data processing solutions on HDFS handling 10B+ records for large-scale audience segmentation and feature generation • Built ETL pipelines transforming diverse data sources into model-ready formats with complex business logic • Optimized data processing workflows for performance and scalability across distributed systemsProduction Systems: • Prototyped neural network training pipeline integrating TensorFlow, feature selection, PCA, and automated hyperparameter optimization with systematic backtesting • Collaborated with software engineers, QA, and product managers to ship production features and resolve critical system issues • Maintained Linux-based development environments with Git version control and CI/CD best practicesTechnologies: Python, Spark, Scala, TypeScript, SQL, TensorFlow, Scikit-learn, HDFS, MariaDB, Docker, Linux, Git, Protocol Buffers

Education

• Louisiana State University

  Master's degree, Business Administration and Management, Analytics

  2018 — 2020

• Louisiana State University

  Bachelor of Engineering (B.Eng.), Mechanical Engineering

  2012 — 2016