Industrial R&D Statistics & Experimentation Leader

General Mills Inc.; United States; On-site; USD 129,000 - 193,000; Full time

Job summary

General Mills is seeking an R&D Manager of Industrial Statistics and Experimentation to lead a team of five statisticians and data scientists within our global R&D organization. This player/coach role balances people development with hands-on project leadership, embedding statistical rigor across product and process development.

You will partner with Product Development, Process Development, Quality, and Operations, driving DOE-centric experimentation, end-to-end design, and data-driven

Qualifications

• Master's degree in statistics or related quantitative field.
• 8+ years of applied/industrial statistics experience in R&D or product/process development.
• 2+ years of people leadership, with matrixed collaboration.
• Strong DOE and modeling experience (ANOVA/regression/GLM; mixed models).
• Proficiency with JMP/Minitab and R or Python.

Responsibilities

• Lead, coach, and influence a high-impact team.
• Set standards for engagement and operating rhythms across the team.
• Guide end-to-end Design of Experiments strategy (DOE) and full-cycle experimentation.
• Oversee analyses using ANOVA/regression/GLM; apply multivariate methods.
• Translate complex statistical findings into actionable cross-functional recommendations.

Skills

Leadership

DOE expertise

Statistical modeling

Cross-functional collaboration

Education

Master's Degree in Statistics or related field

Ph.D. in Statistics or related field

Tools

JMP

Minitab

R

Python

Job description

General Mills is seeking an R&D Manager of Industrial Statistics and Experimentation to lead a team of five statisticians and data scientists within our global R&D organization. This player/coach role balances people development with hands-on project leadership, embedding statistical rigor across product and process development.

You will partner with Product Development, Process Development, Quality, and Operations, driving DOE-centric experimentation, end-to-end design, and data-driven