At Cavnue, we believe that information is at the center of the future of infrastructure. As a senior data scientist, you’ll be responsible for not just thinking about what the best model is to solve the problems of mobility today, but thinking about data sets that don’t exist and solutioning how we might build systems to gather them. You’ll be expected to have experience working with transportation data, economic models, and product penetration rates to build a crystal ball about the future of road travel on ten and twenty-year horizons. Whether it’s understanding how climate change might change freight in fifteen years or thinking about how sports success shapes a city’s rapid transit, we’re looking for a thought leader who can rigorously answer these questions for commercial partners, municipal governments, and car enthusiasts.
Working to solve some of the most complex and challenging problems facing road and traffic operations today, in support of Cavnue’s mission to build the future of roads.
Working together with Cavnue Product and Business Development leadership to solve high-value data science problems for Cavnue’s customers.
Developing models and algorithms to solve key problems such as pricing optimization, vehicle identification, travel time estimation, and maintenance optimization, based on machine learning, statistics, and optimization.
Analyzing and improving data sources and developing and improving metrics for Cavnue customers and internal use.
Working with Engineering and Product teams to productionize these algorithms and models to create impact at scale in a real-world setting.
Proposing and guiding data analytics throughout the organization to drive business insights and facilitate decisions.
Establishing standard methodologies and best practices for all internal and external data analytics.
Master’s degree in Computer Science, Mathematics, Engineering, or related field; Ph.D. is a plus.
Expert knowledge of statistics, machine learning, and optimization.
Significant experience with a scripting language (e.g. Python) and with an object-oriented language (e.g. C++).
Firm grasp in the development, validation, implementation, and production launch of advanced analytics models and algorithms.
Experience with utilizing a clustered distributed-data processing tool such as Hadoop, Spark, Dask, Map-reduce, and Hive is a plus.
An incredible ability to communicate technical concepts and solutions at a level appropriate for technical and non-technical audiences.
Experience with processing, analyzing, and modeling with traffic, geospatial, and weather data a plus
This position requires candidates who are comfortable with developing v1.0 products and prototypes in a scrappy manner and thrive in an entrepreneurial environment.