Sr. Data Scientist - Applied Machine Learning and Optimization
Dairy Farmers of America Kansas City, Kansas, United States
Dairy Product Manufacturing · 10,001+ employees
Applying here? Try the free cover letter tool — paste this posting and your résumé, no account needed.
About the role
The role involves framing complex business problems into analytical and optimization solutions while partnering with engineering teams to deploy models into production. You will be responsible for the full model lifecycle, including data exploration, model development, validation, and monitoring for performance and drift.
What they look for
Requirements
Candidates must have at least 6 years of experience in data science or a related quantitative field and hold an undergraduate degree in a relevant discipline. Proficiency in Python, SQL, and cloud platforms like Snowflake and Azure is required, along with strong knowledge of machine learning and statistical modeling.
Full description
Serve as an experienced individual contributor responsible for framing business problems as analytical, statistical, predictive, and optimization solutions; developing and validating models; and partnering with engineering teams to move approved models into governed production use. Use Python, SQL, Snowflake, Azure, and appropriate modeling methods to create explainable, reproducible, and measurable solutions while applying responsible AI, data governance, privacy, security, and MLOps standards throughout the model lifecycle.
Job Duties and Responsibilities:
- Partner with business owners, analysts, and subject-matter experts to translate operational problems into testable hypotheses, objective functions, constraints, target variables, evaluation criteria, and measurable business outcomes.
- Explore and profile enterprise data; identify data limitations, bias, leakage, missingness, quality concerns, and suitability for statistical, predictive, optimization, or AI/ML methods.
- Design and develop statistical analyses, forecasting models, predictive models, machine-learning solutions, and mathematical optimization approaches appropriate to the business problem.
- Perform feature engineering in partnership with data engineers and analytics engineers, using governed and reproducible data inputs rather than unmanaged one-off datasets.
- Build baselines, select methods, conduct experiments, tune models, and evaluate results using appropriate holdout, cross-validation, back-testing, scenario, sensitivity, and error-analysis techniques.
- Document model assumptions, intended use, limitations, training data, features, evaluation results, fairness or risk considerations, explainability, thresholds, and human-oversight requirements.
- Validate model outputs with business SMEs, compare recommendations with historical and scenario-based outcomes, and incorporate approved feedback without obscuring model limitations.
- Collaborate with data engineering and MLOps resources to package, register, deploy, monitor, retrain, version, and retire models through controlled environments and release processes.
- Define and monitor model-performance, drift, data-quality, business-outcome, and operational metrics; investigate degradation and recommend corrective action.
- Create clear visualizations, analytical narratives, model cards, experiment records, and decision-support materials for technical and nontechnical audiences.
- Apply enterprise AI governance, responsible AI, privacy, security, architecture, SDLC, and regulatory requirements; surface residual risks and obtain required approvals before production use.
- Advance reusable modeling practices, peer review, testing standards, and knowledge sharing across the team; provide technical guidance on complex analytical work.
- The requirements herein describe the general nature and level of work performed by the employee but are not a complete list of responsibilities, duties, and skills required. Other duties may be assigned as needed.
Qualifications
Minimum Requirements:
Education and Experience
- Undergraduate degree in Data Science, Statistics, Mathematics, Operations Research, Computer Science, Engineering, Economics, or a related quantitative field; graduate degree preferred for roles with advanced optimization or research responsibilities.
- 6+ years of experience in data science, applied statistics, operations research, machine learning, optimization, or a related quantitative discipline.
- Advanced proficiency with Python and SQL and experience using common data-science, statistics, machine-learning, and optimization libraries.
- Experience developing models using Snowflake or comparable cloud data platforms and working with Azure-based data, application, or ML services.
- Experience with problem formulation, feature engineering, experiment design, model selection, model evaluation, explainability, and communication of uncertainty and limitations.
- Experience moving models beyond notebooks into versioned, testable, monitored, and supportable production workflows in partnership with engineering teams.
- Experience with forecasting, predictive modeling, mathematical optimization, or decision science; operations research and constraint-based optimization experience strongly preferred when supporting planning and scheduling use cases.
- Knowledge of responsible AI, model risk, data privacy, security, governance, and documentation practices.
- Relevant Azure, Snowflake, data science, ML, or analytics certification preferred.
Knowledge, Skills and Abilities
- Deep knowledge of statistical reasoning, machine learning, model evaluation, experimentation, and the appropriate use and limitations of quantitative methods.
- Able to frame ambiguous business problems, distinguish predictive questions from optimization or rules-based problems, and select methods based on evidence rather than novelty.
- Able to evaluate model performance using technically sound and business-relevant measures and clearly explain tradeoffs, uncertainty, limitations, and residual risk.
- Strong Python, SQL, data exploration, feature engineering, visualization, and reproducible research skills.
- Strong understanding of data leakage, bias, drift, explainability, human oversight, privacy, security, responsible AI, and model governance.
- Able to collaborate with data engineers, analytics engineers, MLOps engineers, application teams, analysts, product owners, and business SMEs across the full model lifecycle.
- Able to independently lead complex analytical work, review the work of peers, maintain rigorous documentation, and influence decisions through evidence and clear communication.
- Able to balance model accuracy with interpretability, operational constraints, reliability, cost, maintainability, and business adoption.
- Must be able to read, write, and speak English.
Similar roles
-
Stage MLOps Engineer / Data Scientist – Industrialisation des workflows Machine Learning sur Databricks (F/H)
AXA Suresnes, Ile-de-France, France
-
Senior Machine Learning Engineer (W/M/X)
Ubisoft Paris, Ile-de-France, France
-
Machine Learning TTS Engineer
Acclaim Astana, Kazakhstan
-
AI Architect (m/w/d) | Machine Learning & Agentic AI
Bertelsmann-Jobs Gütersloh, North Rhine-Westphalia, Germany
-
Senior Consultant Data Science & Machine Learning (w/m/d)
talentbird GmbH Vienna, Austria · €70K/yr
-
Senior Machine Learning Engineer, Decision Intelligence
Humana United States · $107K–$147K/yr