AI/ML Engineering Intern

MasterControl•Salt Lake City, UT

9h•$35 - $50•Onsite

About The Position

MasterControl is looking for a Machine Learning Intern to help build AI capabilities for life-sciences quality and manufacturing. Our AI/ML platform combines predictive machine learning, self-hosted language models, and governed analytical workflows to help customers identify quality risks, investigate deviations, and understand manufacturing performance. You will work alongside data scientists, ML engineers, and platform engineers on real manufacturing execution records and quality-event data. This internship offers hands-on experience across data preparation, model development, evaluation, and production integration, with projects scoped to your experience and supported by technical mentorship.

Requirements

Currently pursuing a degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, or a related field.
Proficiency in Python and familiarity with scikit-learn, PyTorch, or a comparable machine learning framework.
Experience working with Pandas and NumPy, along with basic SQL skills for exploring and preparing data.
Understanding of regression, classification, clustering, feature engineering, training and validation splits, overfitting, and model evaluation.
Familiarity with Git; an ability to write readable, testable code; and a willingness to investigate unexpected results, document findings, and collaborate across disciplines.

Nice To Haves

Coursework, research, or personal projects involving time-series or sequential data, anomaly detection, imbalanced classification, text embeddings, information retrieval, or open-source language models.
Exposure to Docker, Linux, Spark, cloud infrastructure, or model-serving APIs is also valuable.
Prior life-sciences experience is not required.

Responsibilities

Prepare data and develop features. Help transform manufacturing records, quality events, and related operational data into reliable training and evaluation datasets. Investigate data quality, missing values, and relationships between process execution and quality outcomes.
Build and evaluate predictive models. Contribute to models for operational risk scoring, early batch-outcome prediction, recurring deviations, and nonconformance risk. Compare simple statistical and machine learning baselines with more advanced approaches.
Support semantic search and quality-event analysis. Experiment with text embeddings, clustering, and retrieval methods to identify similar deviations, organize unstructured information, and improve access to relevant evidence.
Contribute to governed language-model applications. Help develop and test capabilities that interpret user questions, connect them to approved analytical procedures, and produce responses grounded in computed results and supporting evidence.
Run rigorous experiments. Create reproducible evaluations, investigate failure cases, and document findings. Apply appropriate validation methods, prevent data leakage, and assess performance beyond overall accuracy, including false positives, calibration, and prediction lead time where relevant.
Help integrate models into production. Write and test Python services and APIs, contribute to training and inference pipelines, and measure reliability, latency, and computational efficiency under the guidance of ML and platform engineers.
Maintain reproducibility and traceability. Document datasets, features, model configurations, experiments, and evaluation results. Follow team practices for version control, testing, customer-data isolation, and secure data handling.