RESPONSIBILITY
• Guide measurement, strategy, and tactical decision-making across the company across a variety of teams and levels. Data Scientists at DoorDash work to uncover insights and turn them into relevant recommendations, driving decisions for the entire organizationForecast the supply of available dashers as well as incoming delivery demand
• Use quantitative analysis and the presentation of data to see beyond the numbers and understand what drives our business
• Build full-cycle analytics experiments, reports, and dashboards using SQL, R, Python, or other scripting and statistical tools
• Work alongside of mentor junior analysts on how to use more advanced methods and solve challenges
• Produce recommendations and use statistical techniques and hypothesis testing to validate your findings.
• Provide insights to help business and product leaders understand marketplace dynamics, user behaviors, and long-term trends
• Identify and measure levers to help move essential metrics and make recommendations
• Work backwards from understanding and sizing problems to ideating solutions
• Report against our goals by identifying essential metrics and building executive-facing dashboards to track progress
• Collaborate with engineering to implement, document, validate, and monitor our logging
• Iterate and improve our recommendation, personalization and ranking algorithms which have applications in several product areas like search, autocomplete and email/push communications
• Build models for next generation pricing and pay algorithms
• Improve models used in real time vehicle routing in major metropolitan areas, to help our dashers arrive at desired locations with little to no lag/latency
• Predict preparation time for over 50,000 merchant partners
QUALIFICATIONS
• A degree in Math, Physics, Statistics, Economics, Computer Science, or similar domain
• Good understanding of many quantitative disciplines such as statistics, machine learning, operations research, causal inference, and deep understanding in at least one
• Demonstrated familiarity with programming languages e.g. python and machine learning libraries e.g. SciKit Learn, Spark MLLib
• Understanding of experimentation techniques e.g. A/B testing
