Data Scientist - Valuation Services

Key Skills

Algorithms, Amazon RedShift, Apache Hive, API, AWS Glue, AWS Sagemaker, Batch Data Processing, Data Modeling, Data science techniques, Data Visualization, Java Programming, Lambda, Machine learning techniques, MySQL, Python Programming, R Programming, SPARK Programming, SQL, Terabyte scale datasets

Job Description

As part of the Valuation Services division of JD Power, you will work to understand the features that drive the price of a vehicle and predict what future vehicle values will be. Our data science team is accountable for every data point we output and provides accurate, transparent, industry-leading analytics. We are looking for a Data Scientist who will have the freedom to utilize the latest technologies to solve challenging problems, create innovative machine learning processes from the ground up, deploy them into production on our AWS server, and develop the tools for monitoring them. We are a mature and tight-knit data science team looking to add another top-shelf team member who is ready to make a difference in the automotive industry. Join us! 

The Impact:

We make data products and every new data product we output will solve a problem in the auto industry. Every Data Scientist will build models that go into production and directly impact our core products.

About the Job:

• Experience daily immersion in automotive industry data.
• Build, maintain and iterate on production machine learning algorithms. Develop production code and automate algorithms at scale.
• Collaborate closely with technology and engineering teams to improve existing processes and build out new ones. Work with product team to research and develop the analytics that will power new products.
• Create visual reports in Tableau to monitor data pipelines, ensure quality, and summarize findings. Share results and interpretations with internal and external clients.
• Enjoy a team environment that encourages sharing of ideas to build the best predictive algorithms. 
• Perform ad-hoc data analysis and reporting?using statistical software.

Primary responsibilities are:

• Define, develop, and maintain a variety of data solutions including, but not limited to the following: use Python to automate predictive machine learning algorithms at scale, research data solutions, develop production

code, and deploy inferential machine learning algorithms; custom OEM consulting study analytics; and develop model performance monitoring data pipelines and visualizations.

• In charge of producing and auditing data feeding the Residual Value Edition, ALG’s core product, serving all automakers and financial institutions across North America to support strategic decisions.
• Collaborate closely with Data Warehouse, and Engineering teams utilizing software such as Python, SQL, Tableau, and the AWS cloud services suite to build data pipelines for existing and new products.
• Success will depend on learning the details of our data flow and managing the production, application, and QA of data required to create our residual values each edition.
• The Data Science team has 12 members, and it is likely that this position will interact with all of them, but most closely with the Product Data Science team and Modeling teams.??

What you Need:

• Enthusiasm for the automotive industry?
• Curiosity and passion for solving problems with data?
• Ability to communicate complex ideas to any audience, ranging from teammates to executives?
• 1+ years of professional experience working with large datasets?
• 1+ years of professional experience with statistical programming software (Spark, R, Python preferred)?
• 1+ years of professional experience with database software (RedShift, Hive, SQL, MYSQL)?
• 1+ years of professional experience deploying cloud based automated analytic processes??
• Master’s Degree in Statistics, Data Science, Economics, or related field

Nice to Have:

• Experience with automotive market data?
• Experience working with AWS tools (like Sagemaker, Glue, Batch, Lamdba)?
• Some shareable examples of data visualizations you have created?
• Experience deploying machine learning models into production with an API
• PhD in Statistics, Data Science, Economics, or related field??
• Love of Fast and Furious franchise?

The Career Opportunity:

Grow as a full stack data scientist as part of a medium sized team. You will pipeline data, build models, deploy them in the cloud, and build monitoring suites.