Top Data Science Jobs in Provo, UT

Lead end-to-end data science initiatives for commercial property or homeowners insurance: acquire and prepare data, build and validate predictive models, deploy and monitor production models, ensure governance and documentation, advise teams, and evaluate emerging ML/AI techniques to improve pricing, risk selection, and underwriting outcomes.

Design and implement advanced ML models for real-time forecasting and decision support, ensure data provenance and lineage, integrate federated geospatial and multi-format data, produce ROM and quarterly cost/resource reports, and apply Agile sprint practices to deliver mission-aligned analytics for DoD/IC customers.

As a Senior Data Scientist at Yahoo Mail, you will enhance user growth strategies via product innovation, overseeing research projects and analytics.

Develop and validate SDTM and ADaM datasets using R per CDISC standards, support TLF generation in R or SAS, perform QC and reconcile data issues, collaborate with biostatistics and clinical teams, and contribute to automation and reproducible workflows for regulatory submissions.

Build, ship, and own end-to-end ML models for vendor matching, order routing, and supply-chain optimization. Partner with data engineering to productionize models, quantify impact, document work, and implement decision logic components toward agentic AI in a fast-moving healthcare startup environment.

Lead development of time-series and econometric models (ARIMA, VAR, state-space, WLS, panel data) and Bayesian probabilistic frameworks. Use causal inference and stochastic processes to produce actionable insights, work with large datasets on Databricks, communicate results to stakeholders, and mentor junior team members.

Lead advanced analytics and ML projects: perform EDA, feature engineering, statistical modeling, and build/optimize production ML and Generative AI solutions (LLMs, embeddings, RAG). Collaborate with engineering and MLOps to deploy and monitor models, create visualizations and dashboards, translate insights for stakeholders, and mentor junior team members.

Design, develop, and deploy supervised machine learning models for credit decisioning. Collaborate with business and technical stakeholders to create data sources, improve modeling methodology, operationalize models, and manage model evaluation and risk for production systems.

Design, build, and deploy production-grade generative AI applications: orchestrate multi-agent systems, implement advanced RAG with vector DBs, fine-tune and host LLMs, optimize GenAI workflows, and deliver scalable FastAPI-based backend services with Docker and monitoring.

Design, build, and deploy production generative AI applications: orchestrate multi-agent workflows, implement advanced RAG with vector databases, integrate/benchmark LLMs, fine-tune models, and deploy scalable FastAPI-based services with monitoring, CI/CD, and Dockerized production pipelines.

Design, build, and scale production Generative AI systems: multi-agent orchestration, advanced RAG with vector databases, LLM integration and fine-tuning, scalable FastAPI backends, Dockerized deployment, monitoring, and GenAI optimization for latency, cost, and reliability.

Design, build, and deploy production-grade generative AI systems: multi-agent orchestration, advanced RAG with vector databases, integrate/swap LLMs, fine-tune models, optimize prompts and latency, and containerize services with monitoring and CI/CD.

Build, optimize, and scale production Generative AI applications. Design multi-agent systems and LangGraph workflows, implement advanced RAG with LlamaIndex and vector DBs, fine-tune and deploy LLMs, and create high-performance FastAPI async backends. Improve latency, cost, and reliability, containerize services with Docker, and manage monitoring, API security, and CI/CD for ML deployments.

Design, build, and productionize generative AI solutions: advanced Python development, LLM prompt engineering and fine-tuning, agent frameworks, RAG pipelines with vector DBs, API and cloud deployment, MLOps/LLMOps, model evaluation and Responsible AI practices, and translate business needs into scalable AI applications.

Design, build, and scale production Generative AI applications: multi-agent systems, advanced RAG pipelines, LLM integration and fine-tuning, scalable FastAPI backends, vector search, monitoring, and Dockerized deployments.

Design, build, and deploy production Generative AI applications: orchestrate multi-agent workflows, implement advanced RAG with vector DBs, integrate and fine-tune LLMs, develop scalable FastAPI/async backends, containerize with Docker, and optimize GenAI systems for latency, cost, and reliability.

Design, build, and scale production Generative AI applications including multi-agent systems, advanced RAG pipelines, and local/frontier LLM deployments. Implement high-performance backends with FastAPI and async Python, fine-tune and quantize models, integrate vector databases and retrieval systems, and deploy/monitor containerized AI services for reliability, latency, and cost optimization.

Founding Data Scientist for RC Capital responsible for building underwriting, fraud detection, anomaly detection, and lead-qualification models; integrating risk signals into product flows; deploying and monitoring production models; analyzing cross-platform revenue data; and defining DS strategy to scale fintech products.

Proactively explore RevenueCat data to identify customer problems and opportunities. Translate ambiguous product questions into analyses and production-grade predictive/descriptive models. Partner with Product, Engineering, and Analytics to shape roadmaps, define experimentation and benchmarking approaches, deploy and iterate on models powering customer-facing features, and communicate insights across technical and non-technical audiences.

Design, train and validate supervised ML models on multi-billion claim records to score fraud risk; engineer features in-warehouse; deploy and monitor models in production; provide human-readable rationale and claim-level evidence; collaborate with subject-matter experts and stakeholders to ensure actionable, explainable outputs.

Own complex analyses and measurement frameworks for a product or business area. Design experiments and statistical/causal models, define and monitor KPIs, quantify impact, and translate findings into product and business recommendations. Partner cross-functionally, mentor junior analysts, and use tools like Python, SQL, Snowflake, dbt, Airflow, Spark, and AWS to scale analytics and ensure reproducibility and strong governance.

Lead causal inference and measurement efforts for payments, build and evaluate ML/AI and LLM-based models, optimize fraud mitigation and loss strategies, simulate interventions, and communicate findings to stakeholders to drive product and risk decisions.

Design, build, and productionize complex Bayesian and probabilistic modeling pipelines. Lead methodology and technical direction, collaborate with Product/Data/Engineering, mentor data scientists, communicate results to stakeholders, and apply hierarchical, state-space, time-series, and graphical modeling at scale with strong emphasis on uncertainty and model validation.

Lead research defining fabric's AI shopping roadmap: design and run quantitative studies, build models and benchmarks for AI search (AEO/GEO), run experiments, translate findings into customer-facing insights, and publish research to influence product and go-to-market strategy.

Build and validate production-grade ML and AI systems across pricing, underwriting, claims, and portfolio management. Work with structured and unstructured data, LLMs and agentic workflows, extract information from documents, resolve entities, create feature pipelines and inference services, quantify uncertainty, monitor drift, and measure business impact in collaboration with engineers, actuaries, underwriters, and product teams.