Top Data Science Jobs in Provo, UT

Design, train, fine-tune, deploy, and monitor Large Language Models for government mission applications. Collaborate with cross-functional teams, ensure data preprocessing and model performance, present findings to stakeholders, and mentor junior data scientists.

Support IRS projects by developing, validating, and deploying predictive and statistical models on large tax and financial datasets. Perform data cleaning, feature engineering, anomaly detection, and risk scoring using Python/R, SQL, and Databricks. Communicate results to stakeholders and collaborate with cross-functional teams to inform audit prioritization, fraud detection, and compliance efforts.

Design, develop, validate, and deploy statistical and machine learning models to detect fraud, anomalies, and noncompliance in large tax and financial datasets. Clean and feature-engineer data, run robustness and sensitivity tests, collaborate with stakeholders, and present technical and non-technical findings. Support end-to-end data science lifecycle and productionization in a government environment.

Lead and support full-lifecycle data science projects (forecasting, NLP, classification/regression, optimization). Design production-ready solutions within client environments, consult with stakeholders to define ambiguous problems, communicate technical findings, and develop/teach bespoke analytics training.

Support IRS tax compliance and fraud detection by developing, validating, and deploying predictive and statistical models. Clean and analyze large datasets, apply supervised and unsupervised learning (including NLP and graph analytics), collaborate with clients and teams, and deliver technical briefings and defensible, explainable model results.

Work with clients and technical staff to design, develop, and deploy predictive models and data-driven analytical solutions. Perform data extraction, ingestion, and modeling; evaluate and improve models; translate business rules into technical specifications and communicate results to stakeholders.

Support IRS analytics to detect fraud and non-compliance by developing, validating, and deploying predictive and statistical models. Clean and analyze large datasets, perform feature engineering, apply supervised and unsupervised techniques (including NLP and graph analytics), collaborate with stakeholders, and deliver technical and non-technical briefings. Work across the full data science lifecycle and operate in secure government environments.

Develop, validate, and deploy predictive and statistical models using structured and unstructured tax and financial data to detect fraud and non-compliance. Clean and wrangle large datasets, perform feature engineering, apply supervised and unsupervised techniques, and communicate results to technical and non-technical stakeholders. Collaborate with clients and cross-functional teams and support model deployment and documentation in secure government environments.

Lead design, build, and deployment of production-grade generative AI products (LLM apps, agents, copilots, RAG/search). Rapidly prototype features, build APIs, services, and retrieval pipelines, optimize performance and reliability, ensure responsible AI, translate research into product, and mentor team members.

Lead product experimentation and ML initiatives: design and run A/B tests and causal analyses, build and deploy ML models (GBMs, random forest, logistic regression) using Python and MLflow, partner with Product/Design/Engineering, translate results into executive-facing recommendations, and establish experimentation and ML best practices.

Lead and build Neural Earth's geospatial data science function: design and deploy Python-based geospatial models, architect production geospatial data pipelines, validate reproducible methods, translate scientific outputs into customer-ready products, and manage and mentor at least one direct report while advising customers and stakeholders.

Analyze large marketing datasets, build predictive models for segmentation, pricing, and demand forecasting, support targeted campaigns and retention, partner with product and marketing, apply statistical and ML methods, ensure data quality with engineering, and communicate insights to stakeholders to drive conversion and retention improvements.

Senior individual contributor owning complex end-to-end ML problems for supply chain and consumer applications. Build and deploy predictive models (demand forecasting, delivery ETA, recommendations), embed with engineering teams, define MLOps standards, and advise leadership on data science strategy and investments.

The Data Scientist at GenLogs will build machine-learning systems, analyze large datasets, and collaborate with engineering and product teams to deliver advanced logistics intelligence solutions.

Partner with Marketing as the embedded data science lead to build marketing measurement, attribution, LTV/ROAS/CAC models, run experiments, analyze the full funnel, create forecasts and dashboards, and influence channel strategy and budget allocation.

As the Staff Data Scientist, you will lead the data science function, driving strategy, mentoring peers, and shaping product direction through advanced analytics and experimentation.

The Marketing Data Scientist will analyze data, onboard clients, develop data pipelines in R, and propose improvements to enhance efficiency.

As a Data Scientist, you will analyze blockchain data to derive insights, develop and deploy predictive models, and improve product offerings.

Design and deploy scalable data science and generative AI solutions: acquire and ETL data from S3/RedShift/Spark, analyze data quality, build/validate models (ML, NLP, networks), deploy models to production, and mentor teams while collaborating with stakeholders and engineering.

Lead company-level measurement and causal strategy, define MAU×ARPU metrics and semantic mart, set scientific standards for experimentation and analysis, own strategic models (MMM, elasticity, forecasting), partner with engineering to productionize analytics, and raise org-wide scientific maturity through governance, templates, and upskilling.

Own and evolve revenue calibration models tying CX interactions to revenue, design causal inference and experimentation frameworks, build LLM-powered classification/NLP pipelines, productionize models with Analytics Engineers, define segmentation and behavioral signals, and ensure statistical rigor for executive reporting and regulatory defensibility.

Design, develop, and deploy production-grade generative AI and agentic systems (LLMs, RAG, AI agents). Build document intelligence, retrieval pipelines, vector search, and monitoring frameworks. Collaborate with risk, compliance, product, and engineering to deliver scalable, governed GenAI solutions in regulated environments.

As a Data Scientist/Machine Learning Engineer, you'll finetune models, improve data quality, add new signals, and push solutions to production.

The Data Scientist will build machine learning models to enhance claim audits, optimize performance, and improve healthcare decision-making by analyzing complex data sets.

Design and evaluate causal inference experiments and causal ML models to measure product impact, optimize resource allocation, and inform support operations. Build, deploy, and iterate statistical/ML models, analyze tradeoffs, collaborate cross-functionally, and communicate insights to influence decisions and scale data science capabilities.