The Data Scientist will be part of the Machine Intelligence and Analytics team. This team sits within our Systems Development organization and will be responsible for establishing and maintaining the architecture and analytics to ensure data is usable in a real time manner between the pod, tube, track, etc.

RESPONSIBILITIES

• Perform extract, transform, and load operations on large datasets from many complex, heterogeneous data sources
• Explore, interpret, and analyze datasets for patterns of interest and opportunities for incorporating data driven machine intelligence to vehicle, transportation, and logistics software systems
• Research, evaluate, and determine the best fit of analytical tools and techniques
• Develop or modify existing machine learning tools and libraries as needed
• Develop visualizations of key parameters and relationships to provide insight into data and underlying system.
• Develop, evaluate and adapt advanced machine learning algorithms to transportation and logistics problem domain
• Design and create data mining architectures/models/protocols, statistical reporting, and data analysis methodologies
• Enhance, scale, and deploy real-time analytics capabilities, models, and visualizations within production environment on production compute architecture
• Develop metrics and evaluation criteria to characterize and quantify system performance and benefits of machine intelligence
• Develop, update, and maintain design specification and end user documentation
• Collaborate in a fast-changing environment and to communicate clearly and effectively with colleagues who range from data scientists, developers, dev ops, hardware engineers, and product managers.

BASIC QUALIFICATIONS

• 3 to 5 years working in a similar position
• Master’s degree or PhD in Computer Science or a highly quantitative discipline.
• Strong programming ability with C, C++, and Python
• Strong knowledge in software engineering principles
• Strong mathematical foundation in statistics and linear algebra
• Strong background in Computer Vision, Artificial Neural Networks, Bayesian Networks, Markov Decision Processes, Support Vector Machines, and other cutting edge machine learning methodologies.
• Fast prototyping skills, including comprehensive feature integration during all cycles of development
• Working knowledge of distributed computing architectures and databases
• Academic, or working knowledge, in manipulating large datasets and performing data analytics with machine learning tools.
• Experience with relevant open source, commercial, and scientific software packages
• Self-starter with ability to work in a high paced dynamic environment with only general oversight and direction

PREFERRED QUALIFICATIONS

• Demonstrated ability with the following programming languages: Java, Matlab, R
• Experience with the following software packages: CUDA, Tableau, OpenCV, ROS, TensorFlow, Café, Alchemy, SAS, Genie, Deep Dive, PostgreSQL, NoSQL, Apache products (Spark, Hadoop, Hive, etc.)
• Ability to provide solutions to a variety of technical problems of increasing scope and complexity
• Domain expertise and knowledge of transportation, logistics, and autonomous systems
• Excellent communication skills