NHL Data Scientist at Swish Analytics

San Francisco, California, United States -

Full Time

Start Date

Immediate

Expiry Date

06 May, 26

Salary

130000.0

Posted On

05 Feb, 26

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Machine Learning, Statistical Models, Feature Sets, Model Development, Model Deployment, Experimentation, SQL, Python, GitHub, CI/CD, AWS, Leadership, Communication, Probability Theory, Bayesian Statistics, MCMC

Industry

Spectator Sports

Description

Company Description Swish Analytics is a sports analytics, betting and fantasy startup building the next generation of predictive sports analytics data products. We believe that oddsmaking is a challenge rooted in engineering, mathematics, and sports betting expertise; not intuition. We're looking for team-oriented individuals with an authentic passion for accurate and predictive real-time data who can execute in a fast-paced, creative, and continually-evolving environment without sacrificing technical excellence. Our challenges are unique, so we hope you are comfortable in uncharted territory and passionate about building systems to support products across a variety of industries and consumer/enterprise clients. Job Description Swish Analytics is looking for an NHL Data Scientists to join our ever-growing team! Data Science is at the core of our business, so this team has true ownership and impact over developing core components of Swish's data products. This position is remote from the USA. Duties: Ideate, develop and improve machine learning and statistical models that drive Swish’s core algorithms for producing state-of-the-art sports betting products. Develop contextualized feature sets using sports specific domain knowledge. Contribute to all stages of model development, from creating proof-of-concepts and beta testing, to partnering with data engineering and product teams to deploy new models. Strive to constantly improve model performance using insights from rigorous offline and online experimentation. Analyze results and outputs to assess model performance and identify model weaknesses for directing development efforts. Adhere to software engineering best practices and contribute to shared code repositories. Document modeling work and present to stakeholders and other technical and non-technical partners. Requirements: Masters degree in Data Analytics, Data Science, Computer Science or related technical subject area Demonstrated experience developing models at production scale for hockey or sports betting for 2+ years Expertise in Probability Theory, Machine Learning, Inferential Statistics, Bayesian Statistics, Markov Chain Monte Carlo methods 5+ years of demonstrated experience developing and delivering effective machine learning and/or statistical models to serve business needs in sports or sports betting Experience with relational SQL & Python Experience with source control tools such as GitHub and related CI/CD processes Experience working in AWS environments etc Proven track record of strong leadership skills. Has shown ability to partner with teams in solving complex problems by taking a broad perspective to identify innovative solutions Excellent communication skills to both technical and non-technical audiences Base salary: Starting at $130,000 Swish Analytics is an Equal Opportunity Employer. All candidates who meet the qualifications will be considered without regard to race, color, religion, sex, national origin, age, disability, sexual orientation, pregnancy status, genetic, military, veteran status, marital status, or any other characteristic protected by law. The position responsibilities are not limited to the responsibilities outlined above and are subject to change. At the employer’s discretion, this position may require successful completion of background and reference checks.

Responsibilities

The role involves ideating, developing, and improving machine learning and statistical models that drive core algorithms for state-of-the-art sports betting products. Responsibilities also include contributing to all stages of model development, from proof-of-concepts to deployment, and constantly improving performance through rigorous experimentation.