C H Robinson Worldwide Data Scientist in Eden Prairie, Minnesota

We're on a mission to disrupt the logistics industry and take our technology to new heights. We are looking for a Data Scientist that has a passion to understand the details of our business and technology, clarify requirements, transform data into actionable insights, work on innovative projects, combine expert statistical modeling knowledge with machine learning plus other AI and deliver on critical projects. Those who love to work with data will see this as a tremendous opportunity to improve the world's supply chains. In this role you will be responsible for designing and developing algorithms and models to "mine" insight for decision support and predictions in key areas in our technology. This person will work with many groups in IT and as well as the business. Responsibilities: Develop and plan required analytic projects In conjunction with data owners and subject matter experts, develop new ways of getting insights out of data that allow us to improve supply chain logistics Advocate, evangelize and build data-fueled products that help our customers and partners improve business outcomes Understanding root causes of changes in metric Develop algorithms that can go from prototype to production quickly Collaborate with business leaders, subject matter experts, end users, development teams, and other stakeholders to develop analytical solutions and apply the solutions in our technology Authoritative quantitative analysis skills, particularly in machine learning, multivariate statistical modeling, and data mining. Provide and apply quality assurance best practices for data mining/analysis services Use data mining, model building, and other analytical techniques to develop and maintain predictive models Qualifications: Required Qualifications: Working in python primarily, with a variety of technologies (Hadoop, Spark, Hive, MySQL, Docker) to access data and deploy models. Minimum of 3 years of professional experience with machine learning, statistical analysis, predictive modeling, and time series analysis Minimum of 3 years of experience in data mining using databases in an environment with complex data sets Proficiency in computer programming using technologies and languages like C++, Java, R, Python, Scala or related Proficient in data visualization using tools like Python and R and experience with a web-based visualization tool such as (Shiny, D3 or Plotly) Strong knowledge of machine learning algorithms, both using and creating Deep understanding of statistical, predictive and descriptive modeling concepts, machine-learning approaches, clustering and classification techniques, and recommendation and optimization algorithms Familiarity with data-product delivery through HTML-based platforms like Shiny, OpenCPU, DeployR Experience working within cross-functional project team to understand requirements and deliver solutions Strong communication and interpersonal skills and ability to work in team environment Knowledge of relational database and multi-dimensional concepts with ability to perform complex queries in a SQL Server environment. Experience with data sources like MongoDB, Redis, Elastic, Hadoop helpful, but not required Combines creativity, problem-solving skills, and a can-do attitude Passionate about empirical research, asking and answering questions in large datasets, finding patterns and insights within structured and unstructured data Quick and scrappy learner who adapts well to a fast-moving environment and gets things done Preferred Qualifications: Knowing geospatial Experience designing and evaluating the results of complex controlled experiments Knowledge of software systems, design principles, architecture guidelines, and general functioning of middleware & messaging systems along with Service Oriented Architecture (SOA) Working in an Agile-minded environment Education: Academic background in operations research, applied statistics, data mining, machine learning, physics