Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I'm Nicholas Bradley Johnson, a machine learning engineer and data infrastructure architect based in Traverse City, Michigan. With over 12 years of experience, I build scalable data pipelines and deploy production ML models in insurance and fintech, delivering real-time inferences with Python, Spark, and AWS that cut latency by 28% and support high-volume structured and unstructured data streams. Expertise includes Snowflake, Terraform, Docker, Prefect, feature engineering, model serving, ML Ops workflows, and CI/CD automation with GitHub Actions. I enjoy designing parallel computing solutions, evaluating streaming architectures, and collaborating across teams to productionize algorithms while maintaining reliability and compliance.…Hi, I'm Nicholas Bradley Johnson, a machine learning engineer and data infrastructure architect based in Traverse City, Michigan. With over 12 years of experience, I build scalable data pipelines and deploy production ML models in insurance and fintech, delivering real-time inferences with Python, Spark, and AWS that cut latency by 28% and support high-volume structured and unstructured data streams. Expertise includes Snowflake, Terraform, Docker, Prefect, feature engineering, model serving, ML Ops workflows, and CI/CD automation with GitHub Actions. I enjoy designing parallel computing solutions, evaluating streaming architectures, and collaborating across teams to productionize algorithms while maintaining reliability and compliance.

Nicholas Bradley Johnson

AI Engineer, Data Scientist, Full Stack Developer, +1





Hi, I'm Nicholas Bradley Johnson, a machine learning engineer and data infrastructure architect based in Traverse City, Michigan. With over 12 years of experience, I build scalable data pipelines and deploy production ML models in insurance and fintech, delivering real-time inferences with Python, Spark, and AWS that cut latency by 28% and support high-volume structured and unstructured data streams. Expertise includes Snowflake, Terraform, Docker, Prefect, feature engineering, model serving, ML Ops workflows, and CI/CD automation with GitHub Actions. I enjoy designing parallel computing solutions, evaluating streaming architectures, and collaborating across teams to productionize algorithms while maintaining reliability and compliance.…Hi, I'm Nicholas Bradley Johnson, a machine learning engineer and data infrastructure architect based in Traverse City, Michigan. With over 12 years of experience, I build scalable data pipelines and deploy production ML models in insurance and fintech, delivering real-time inferences with Python, Spark, and AWS that cut latency by 28% and support high-volume structured and unstructured data streams. Expertise includes Snowflake, Terraform, Docker, Prefect, feature engineering, model serving, ML Ops workflows, and CI/CD automation with GitHub Actions. I enjoy designing parallel computing solutions, evaluating streaming architectures, and collaborating across teams to productionize algorithms while maintaining reliability and compliance.

Available to hire

Hi, I’m Nicholas Bradley Johnson, a machine learning engineer and data infrastructure architect based in Traverse City, Michigan. With over 12 years of experience, I build scalable data pipelines and deploy production ML models in insurance and fintech, delivering real-time inferences with Python, Spark, and AWS that cut latency by 28% and support high-volume structured and unstructured data streams.

Expertise includes Snowflake, Terraform, Docker, Prefect, feature engineering, model serving, ML Ops workflows, and CI/CD automation with GitHub Actions. I enjoy designing parallel computing solutions, evaluating streaming architectures, and collaborating across teams to productionize algorithms while maintaining reliability and compliance.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Staff AI/ML Engineer at McKinsey & Company

August 2, 2023 - May 2, 2026

Led development of Spark streaming jobs on AWS ingesting 14K daily claim events into Snowflake, enabling real-time feature computation for fraud-detection models with 32% faster processing. Designed and deployed PyTorch models to Lambda endpoints for low-latency inference, integrating Docker containers and achieving 99.9% uptime on production traffic. Built Prefect orchestrated pipelines combining structured policy data with unstructured notes via Pandas and scikit-learn preprocessing, reducing manual review time by 6 hours weekly. Implemented Terraform modules for EC2 and S3 resources and hardened MLflow experiment tracking to support team-wide model versioning and rollback. Tuned XGBoost classifiers on high-volume streaming and instrumented monitoring with Airflow DAGs, cutting false positives by 23%. Coordinated with actuarial and compliance stakeholders to prioritize model updates, ensuring alignment with business goals and clear communication of technical trade-offs.

Senior Machine Learning Engineer at McKinsey & Company

August 2, 2017 - August 2, 2023

Migrated legacy ETL processes to Spark on AWS EMR and Redshift, handling large volumes of structured policy records with improved query performance. Developed Bash and Python scripts for data validation and cleaning, integrating Docker for consistent execution across environments. Implemented GitHub Actions workflows for automated testing and deployment of data jobs, shortening release cycles. Evaluated real-time streaming options with Kafka and Kinesis to support future model inputs while maintaining data quality standards. Partnered with data scientists to expose clean datasets for experimentation and maintained documentation for cross-team handoffs. Mentored junior engineers on data modeling practices and facilitated regular reviews to align technical decisions with product priorities.

Apple Software Engineer at Apple

February 1, 2013 - May 1, 2014

Built Python ETL jobs using Pandas and NumPy to parse unstructured documents into structured tables stored in MongoDB. Automated scheduling and monitoring with Airflow while scripting utilities in Bash for operational tasks. Provided AWS resources including S3, EC2, and Lambda to support growing data needs. Collaborated with operations teams to troubleshoot data issues and maintain clear runbooks for on-call support. Contributed to sprint planning and code reviews, ensuring consistent delivery quality across distributed teams.

AI/ML Developer at JPMorgan Chase

February 1, 2011 - February 1, 2013

Wrote Python and SQL scripts to validate incoming data feeds and flag anomalies before they reach downstream systems. Supported basic Bash automation for nightly jobs and documented findings for the broader engineering group. Participated in team standups and learned core data engineering patterns through hands-on code contributions. Assisted with testing, small pipeline changes, and communicated progress clearly to senior developers.