Data Scientist

100% Onsite Role. We are looking for a Data Scientist to support advanced analytics and machine learning initiatives in Sacramento, California. This Long-term Contract position focuses on creating practical, production-ready solutions that improve operational decision-making, with an early emphasis on predictive maintenance and fleet performance in asset-heavy environments. The role works closely with business leaders and technical teams to turn complex data into reliable models, useful insights, and scalable AI capabilities. Must have experience in construction, mining, transportation, manufacturing, energy, or other asset-intensive industries

Responsibilities:

• Build, test, and implement machine learning and analytical models using operational, maintenance, and telemetry data to improve equipment reliability and reduce unexpected downtime.
• Create pilot solutions with measurable success criteria, then develop high-performing concepts into stable model pipelines suitable for ongoing production use.
• Convert analytical results into clear recommendations, dashboards, or decision-support outputs that help both technical teams and business stakeholders act with confidence.
• Partner with data engineering teams to shape requirements for data intake, transformation, feature creation, and model delivery across the broader data environment.
• Document methodologies, assumptions, dependencies, and performance results to support transparency, repeatability, and effective model governance.
• Provide input on enterprise data architecture needs from a data science perspective, including dataset design, feature availability, experiment tracking, and model readiness.
• Identify data limitations, quality concerns, and enrichment opportunities that could influence model accuracy or business value.
• Work with cross-functional partners to define new analytics and AI opportunities and assess external tools or vendor-developed solutions when needed.
• Master’s degree or PhD in Data Science, Statistics, Computer Science, Applied Mathematics, Engineering, or another closely related quantitative discipline.
• At least 5 years of practical experience developing and deploying predictive analytics or machine learning solutions in business settings.
• Strong proficiency in Python or R, along with hands-on use of core data science libraries such as pandas, scikit-learn, XGBoost, or LightGBM.
• Experience with large-scale data environments and cloud-based platforms such as Azure, Databricks, or similar technologies.
• Solid understanding of model evaluation, validation techniques, feature engineering, and methods for preventing data leakage.
• Background working with technologies such as Apache Spark, Apache Hadoop, Apache Kafka, and ETL processes is highly desirable.
• Ability to communicate technical findings clearly to varied audiences and translate business needs into effective analytical approaches.
• Experience in construction, mining, transportation, manufacturing, energy, or other asset-intensive industries is Required