BrightDrop Senior Data Scientist - Fleet Analytics and Modeling

Key Skills

C Programming, C++, Cloud computing, Data science techniques, Java Programming, Machine learning techniques, MATLAB Programming, Python Programming, PyTorch, R Programming, Scala Programming, SQL, TensorFlow

Job Description

At BrightDrop, we are reshaping e-commerce by developing smarter, greener, and more efficient ways to deliver goods and services to your door, while delivering a brighter future for the cities where we live. We are building an ecosystem of all-electric, zero-emissions delivery solutions – from electric vehicles, to ePallets and software that leverages real-time data to drive intelligent optimizations for e-commerce. To deliver on our mission we are growing fast and building a team -- based in Palo Alto, with offices in Atlanta and Detroit -- that is customer-focused, agile and passionate about innovating for a more sustainable future.

From engineering to product management and operations, BrightDrop is looking for people who can combine a passion for technology and sustainability with high doses of curiosity and rigorous thinking to deliver a better future. Backed by General Motors, BrightDrop is striving to improve the communities where we live and deliver a better future for generations to come. We hope you’ll join us.

As Senior Data Scientist for Fleet Analytics and Modeling, you will generate timely, actionable insights for our customers across the last-mile delivery sector through retrospective analysis of fleet telemetry data as well as prospective analysis of output from BrightDrop’s meso-scale agent-based simulation environment. You will analyze and evaluate algorithms that optimize last-mile logistics for manually driven and autonomous fleets, in an increasingly on-demand context. You will assist in defining requirements for the on-going development of our data science and machine learning pipeline framework.

Responsibilities:

• Use data processing pipeline systems to implement workflows that enable rapid and flexible insight generation and model development at scale 
• Work with hardware, software, and analytics teams to characterize existing fleets in terms of vehicle performance, business strategy, human behavior, and other dimensions
• Generate visually stunning, highly intelligible, information dense data visualizations for internal and external consumption
• Present results of analyses to technical team members, product team, senior management, and other stakeholders
• Develop robust models of fleet behavior for use in simulation, prediction, and optimization using statistical learning methods
• Assist in the evaluation of novel algorithmic approaches to optimize last-mile, on-demand delivery logistics including advanced energy management and grid-integration of flexible loads
• Work with the Product team to define and innovate the deployment of more efficient, on-demand, electrified goods delivery systems
• Engage with cross functional teams to find opportunities to create unique, data-driven products that drive long-term engagement with our software 

Additional Description

Qualifications

Required:

• Master’s degree or equivalent experience in computer science, data science, engineering, or related quantitative field
• 5+ years of industry experience developing and deploying data-driven insights in transportation mobility systems, gaming, scientific simulation, product R&D, or related field 
• Track record developing innovating solutions to solve complex logistical problems at scale 
• Deep experience with Python, Jupyter, SciKit Learn, and associated tools for statistical and machine learning 
• Experience working in teams using agile software development methodologies together with distributed version control systems (e.g., git) 

Preferred:

• Experience using big data analytics and workflow orchestration tools at scale (e.g. UbiOps, Luigi, Airflow, Spark, etc.) 
• Experience with A/B testing of data-driven, customer facing products
• Experience integrating simulation systems with distributed, data-intensive processing or analytics applications
• Domain knowledge in transportation and energy systems, graph algorithms, convex optimization, and/or reinforcement learning 

Desired:

• Experience designing backend data pipelines (framework selection, DAG design, etc.) 
• Expertise in R 
• Self-driven with a passion for transportation decarbonization
• Adherence to clean code principles

About GM

Our vision is a world with Zero Crashes, Zero Emissions and Zero Congestion and we embrace the responsibility to lead the change that will make our world better, safer and more equitable for all.