Lead/Senior Quantitative Analyst, Predictive Modeling

• →Conduct and oversee statistical forecasting projects in multiple baseball subject areas
• →Collaborate with baseball subject matter experts in scouting, development, biomechanics, machine learning, decision science, and more, integrating their expertise into player evaluation models
• →Maximize organizational impact of the department’s player evaluation models by advocating model-driven decision-making in various baseball contexts
• →Ensure projects conform to best practices for implementing, maintaining, and improving predictive models throughout their life cycles
• →Assist and mentor other members of the QA team with their projects by providing guidance and feedback on your areas of expertise within baseball and statistical modeling
• →Continually enhance your and your colleagues’ knowledge of baseball and data science through documentation, reading, research, and discussion with your teammates and the rest of the front office

• 2-5+ years of relevant work or graduate school experience
• Possess or are pursuing a BS, MS or PhD in Statistics or related (e.g., mathematics, physics, or ops research) or equivalent practical experience
  ○ To determine leveling we look at a variety of factors including, but not limited to,
  years of experience and education. Typically we consider candidates as Lead QA
  around 2-3 years of experience and Senior QA around 4-5+ years of experience
• Proficiency with scripting languages such as Python, statistical software (R, S-Plus, SAS, or similar), and databases (SQL)
• Demonstrated experience designing, constructing, implementing, and leading technical research projects for use by non-technical stakeholders
• Proven willingness to both teach others and learn new techniques
• Willingness to work as part of a team on complex projects
• Proven leadership and self-direction

• Experience with a probabilistic programming language (Stan, PyMC, etc.)
• Experience managing or overseeing the work of other data scientists or analysts
• Experience with model-driven decision-making under uncertainty (eg. a rigorous approach to fantasy sports, poker, etc.)

The R&D department has been asked to identify the best defensive center fielder in baseball. What models would you build to answer that question, and how would you apply those models to decision-making? (250 word limit)