Senior Data Scientist - Model Evaluation

SumerSports LLC

$135K — $165K *
US-AnywhereRemote in United States
Information Technology
Less than 5 years of experience
Job Overview by Ladders

Qualifications

  • Strong statistical foundations in calibration and reliability.
  • Experience in model evaluation within a production ML team.
  • Knowledge of production ML pipelines and handling common issues like schema drift.
  • Ability to build and extend evaluation tooling independently.
  • Self-starter who shapes their own strategic path.
  • Proficient in integrating AI to enhance evaluation processes.
  • Familiar with complex domains, especially in sports analytics.

Responsibilities

  • Drive end-to-end model evaluation for football ML models.
  • Develop and enhance testing tools for model comparison and deployment.
  • Collaborate with subject-matter experts to align evaluations with model applications.
  • Identify and resolve regressions prior to product launches.
  • Challenge stakeholders on metrics that may misrepresent model performance.
  • Create an experimentation framework for rapid idea testing.

Benefits

  • Comprehensive health insurance plan.
  • Retirement savings plan (401k) with company match.
  • Remote working environment.
  • Flexible, unlimited time off policy.
  • Generous paid holiday schedule, including the Monday after the Super Bowl.
Full Job Description
Position Summary

The Senior Data Scientist will be focused on model evaluation and quality for our football ML models. You'll

contribute to the work that sits between research and production, making sure the models we ship measure what we think they measure. We believe good research is less about having the perfect idea and more about building a rigorous

system for testing ideas. Ideas are plentiful. The real work is designing experiments, learning quickly,

and following the evidence.

Responsibilities

  • Contribute to model evaluation across our football models. Drive one or two threads end-to-end.
  • Build and extend the tooling we use to test, compare, and ship models.
  • Work with football subject-matter experts to design evaluation that reflects how the models will actually get used.
  • Catch silent regressions before they ship.
  • Pushback when a stakeholder asks for a metric that doesn't measure what they think.
  • Build the experimentation harness that lets the team test many ideas fast.


Qualifications

  • Strong statistical foundations. Calibration (reliability and resolution), bootstrapping, inter-rater reliability.
  • Track record contributing to model evaluation on a production ML team.
  • Production ML pipeline experience. You've seen schema drift, label noise, and leakage.
  • You build tooling, not just consume it.
  • Self-starter. Takes strategic direction and shapes their own path.
  • AI-native. Builds skills, loops, and tooling to accelerate evaluation throughput.
  • Stays current with research. Papers, releases, new techniques.
  • Domain absorption capacity. You've gotten fluent on a complex domain (sports, finance, biotech, medical) on a prior job

Bonus Points

  • Football or sports analytics exposure.Experience evaluating tracking-data models.
  • Skill scores for probabilistic forecasts (Brier, etc.).
  • Deep-learning fluency to read training code.
  • Human-in-the-loop ML experience.


Benefits

  • Competitive Salary and Bonus Plan
  • Comprehensive health insurance plan
  • Retirement savings plan (401k) with company match
  • Remote working environment
  • A flexible, unlimited time off policy
  • Generous paid holiday schedule - 13 in total including Monday after the Super Bowl


SumerSports is committed to fair and equitable compensation practices.

Actual compensation packages are based on several factors that are unique to each candidate, including but not limited to skill set, depth of experience, certifications, and specific work location. This may be different in other locations due to differences in the cost of labor.

The total compensation package for this position may also include annual performance bonus, benefits and/or other applicable incentive compensation plans.

The pay range for this role is:

135,000 - 165,000 USD per year (Remote)

Similar Jobs

More Information Technology Jobs

Find similar Senior Data Scientist - Model Evaluation jobs: