All remote jobs

Data Scientist II (Soccer)

AI Summary
Teamworks is seeking a Data Scientist II to develop statistical and machine-learning models that support player recruitment for professional soccer clubs. The role owns the full model lifecycle, including problem formulation, data preparation, validation, deployment, maintenance, and iterative improvement. The successful candidate will work with player tracking and event data, addressing spatial, temporal, noisy, and incomplete observations. Strong Python or R, SQL, reproducible development practices, and rigorous evaluation methods are essential. The position also requires clear communication of model trade-offs and results to technical colleagues and partner clubs.
Remote from
UK, USA
Salary
USD 145k–145k / yr
Employment
Full Time
Experience
Senior
Published
Apply before
9 Dec 2026
Listing views
44
Application actions
1
Application toolkit

Make your next move.

Prepare your resume, explore your fit, and draft a cover letter for this opportunity.

Opportunity details

About this role.

We’re hiring a Data Scientist II on our Soccer team to develop the statistical and machine learning models our partner clubs use for player recruitment. I’m Jacob Mortensen, Senior Manager, Data Science at Teamworks. Our team primarily focuses on building models using both player tracking data and event data to identify undervalued players and characterize the skills that make them effective. The work supports high-stakes recruitment decisions for professional clubs across global football.

The team is managing growing demand from partner clubs alongside model maintenance and new development. This hire will take ownership across the model lifecycle, from design and validation through deployment and improvement. That added capacity will help us move important initiatives forward while keeping our existing models accurate and reliable.

The Role

  • 3+ years of professional or research experience developing statistical or machine learning models in Python or R, with examples of work you personally owned from problem formulation and data preparation through validation and use

  • Strong applied statistical and modeling judgment: you can select appropriate methods, explain their assumptions and trade-offs, and distinguish meaningful predictive signal from artifacts in the data

  • Experience designing rigorous model evaluations, including preventing data leakage, choosing validation strategies appropriate to temporal or grouped data, quantifying uncertainty, and assessing performance across relevant player populations and contexts

  • Experience building models with sports tracking data, including working with spatial and temporal relationships, noisy or incomplete observations, and the data-quality challenges that affect model reliability

  • Ability to write maintainable, tested, and reproducible analytical code, using version control and code review to support collaborative development

  • Proficiency in SQL to join, transform, and validate large, structured datasets used in model development

  • Experience taking models beyond exploratory notebooks into repeatable workflows or production systems, collaborating with engineering and investigating issues as models are used

  • Ability to explain modeling decisions, limitations, and results clearly to technical teammates and professional soccer clubs

What I’m Looking For

What You Must Bring

  • 3+ years of professional or research experience writing code in R or Python for data science, statistics, or machine learning work

  • Comfort with SQL for building and querying structured data

  • Strong data science fundamentals: you understand how models work, what they need from the data, and how to set data up to support them

  • Experience working with sports tracking data, including understanding the kinds of models typically built and the data challenges that come with them

  • Strong communication skills — you’ll be explaining modeling decisions directly to partner clubs, not just internal teammates

Even Better If

  • You have direct experience with soccer data or soccer analytics (inside a team, public work, or academically)

  • You have a demonstrated track record of tackling hard problems through published research, blog posts, conference talks, or public projects

  • Experience using a cloud compute provider (e.g. AWS or Google Cloud) to train and deploy models

  • Comfort using AI coding tools, paired with the judgment to recognize when their output needs to be questioned or corrected

Why This Role

Soccer analytics is moving quickly, and this team is helping shape how advanced modeling is used in recruitment. You’ll have meaningful ownership, room to develop new approaches, and the opportunity to see your work used by professional clubs. You’ll also help define how the team builds, maintains, and scales its model portfolio as demand grows.

This role is not eligible for sponsorship at this time.

Please submit your application through this posting only. We’re unable to review applications or resumes sent via email, LinkedIn, or other channels.

To all recruitment agencies: Teamworks does not accept agency resumes. Please do not forward resumes to our jobs alias, Teamworks employees or any other organization location. Teamworks is not responsible for any fees related to unsolicited resumes.

About Teamworks

We’re the Operating System for Sports™, powering 7,000+ organizations worldwide, from collegiate programs to every major pro league. Founded in 2006, we’ve evolved from a messaging tool for college football into the leading sports tech platform, with 600+ global teammates building the future of sports tech. Our solutions span Personnel, Coaching, Performance, Operations, and Intelligence – helping teams recruit smarter, train better, stay compliant, and win.

Teamworks is an equal opportunity employer – if you live our core values every day and are honest, hardworking, humble, committed, innovative, and an all-around exceptional person, you’ll thrive at Teamworks. We are committed to building a diverse and inclusive workforce and take affirmative action to not discriminate based on race, religion, color, national origin, ancestry, physical disability, mental disability, medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, age, sexual orientation, veteran or military status, or any other legally protected characteristics. This policy applies to all employment practices within our organization, including but not limited to recruiting, hiring, promotion, termination, compensation, benefits, and training. Teamworks is committed to providing reasonable accommodations for candidates with disabilities who need assistance during the hiring process. To request a reasonable accommodation, please email talent@teamworks.com.

Apply now >

This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.

Role DNA

A quick view of the complexity, pace, ownership and collaboration implied by the job description.

Job Complexity

5/5
EasyHard

Pace & Pressure

4/5
RelaxedFast-paced

Autonomy Level

5/5
GuidedFull ownership

Communication Load

4/5
IndependentCollaborative
AI insightThis is a technically demanding applied data-science role involving production-grade modeling, robust validation, uncertainty assessment, and difficult spatiotemporal sports data. The hire is expected to independently own models that influence high-stakes recruitment decisions.

Salary analysis

Estimated compensation compared with the broader US market for similar roles.

Estimated job median (per year)Market rate
$145,000
US market range (per year)$130k–$170k
AI insightThe employer discloses a yearly base compensation amount of $145,000 USD. Estimated US market compensation for a mid-level data scientist with production machine-learning and specialized sports-analytics experience is approximately $130,000–$170,000 USD per year.

Core skills

Skills and capabilities most closely associated with this opportunity.

Sample interview questions
How would you evaluate a player-recruitment model built with temporal tracking and event data?

I would begin with a time-aware validation design that prevents future information from entering training data, such as rolling or season-based splits. I would evaluate predictive performance across relevant player positions, leagues, and game contexts, then quantify uncertainty and investigate calibration as well as aggregate metrics. Finally, I would review outputs with domain experts to ensure that apparent signal is actionable rather than a data artifact.

What are common sources of data leakage in sports analytics, and how would you prevent them?

Leakage can arise when features include information recorded after the prediction point, when the same player appears in both improperly grouped training and test sets, or when preprocessing is fit on all data. I would define the prediction timestamp explicitly, apply grouped and temporal splits before feature processing, and fit transformations only on training folds. I would also document feature availability and add tests to protect the pipeline.

Describe how you would handle noisy or incomplete player-tracking data.

I would first profile missingness by competition, provider, match context, and player population to determine whether it is systematic. Depending on the use case, I would use quality flags, robust feature engineering, appropriately constrained imputation, or exclude unreliable observations. I would measure model sensitivity to these decisions and communicate limitations clearly rather than treating imputed values as ground truth.

How would you move an exploratory model from a notebook into a repeatable production workflow?

I would separate data extraction, feature generation, training, evaluation, and inference into version-controlled modules with tests and documented inputs and outputs. I would create reproducible environment and configuration management, automate validation checks, and work with engineering on deployment, monitoring, and retraining triggers. Post-deployment, I would monitor data drift, performance, and model reliability across player groups.

How would you explain a model's limitations to a professional soccer club making recruitment decisions?

I would lead with the decision the model supports and describe its outputs in football-relevant terms, including confidence and comparison groups. I would be direct about the model's assumptions, data coverage, uncertainty, and cases where its output should be supplemented with scouting judgment. I would use clear examples and visualizations, while avoiding claims that the model can predict outcomes beyond the evidence.

This analysis is generated from the job description. Salary estimates, role characteristics and sample answers are guidance, not employer-provided facts.
Next step

Apply now.

Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information.

Did you apply?Let us know, and we’ll help you track your application.

Continue on the employer website

Protect your personal information and never pay to secure an interview or job offer. .

Log in to save
One quick step before you apply

Sign in to continue.

Sign in or create a free account to continue to the employer's application.

Add alert
Jobs Talent AI Tools Salaries
Menu