Data Scientist

Why Join Us Be part of an organization that’s driving change and consistently recognized as a top employer. At Deluxe, we know that great people build great companies—and we invest in you accordingly. We’re proud to be recognized as a Great Place to Work and a top workplace for Moms, Dads, LGBTQ+ employees, and Veterans. We offer competitive benefits starting on day one, designed to support your life both in and out of work. 42% of our employees have stayed for 10+ years, citing our people, benefits, work-life balance, inclusive culture, and team support as key reasons why. Are you a data scientist who enjoys working directly with clients and making a direct and verifiable impact to their business and the success of your team? Come fill that role on a growing team of data professionals serving large clients across the U.S. The Data Scientist is responsible for leading the development of data-driven solutions for our clients. The role utilizes analytical, statistical, and programming skills to clean, aggregate, and analyze large data sets and interpret results. This position requires a strong command of statistical techniques and machine learning algorithms, as well as a demonstrated practical ability to determine where to invest time, synthesize actionable findings across diverse assignments, and present findings to audiences with diverse agendas and varying levels of technical expertise Responsibilities Include: Querying, pre-processing, data cleaning, feature engineering and analyzing large amounts of structured and Unstructured data(terabytes/petabytes) across multiple data sources using structured query language(SQL), Python, Pytorch, Pyspark, R, Spark and Scala. In a Cloud Native AWS environment. Deliver custom and commercial scalable solutions for internal and external customers. Combine business requirements and existing processes and data knowledge to create analytical solutions by building and deploying unsupervised and supervised machine learning and deep learning models. Including combining models using ensemble modeling techniques. Required to have knowledge and experience in unsupervised learning, principle component analysis(PCA), GLM, lasso/ridge regression, random forest, gradient boosted machines(GBM’s), XGBoost, Baysian optimization, natural language processing(NLP) and deep neural networks/ back propagation. Use advance statistical concepts for sampling, descriptive statistics, hypothesis testing, data quality, performance testing, attribution analysis, multi variate segmentation and recommender systems. Collaborate with other data scientists to solve demanding and complicated business problems by applying machine learning, deep learning to large data sets. Partner with Data Engineering on product development(proof of concept to commercial product), SDLC and CI/CD pipelines to process data, train models, test predictions within a MLOPS framework all at scale and be able to provide requirements for…