Seattle, Washington, United States
Experienced data science leader with a decade of research and industry experience in operations research, machine learning, simulation, experimentation, and reinforcement learning - with a focus on data science in the ride hailing and deliveries domain. Proven track record as tech leader with deep problem solving, technical innovation, industry and academia collaboration, as well as shaping go-to-market strategies for new products. Currently leading the Dispatch data science team at Grab responsible for developing and maintaining the backend algorithms and services for matching of drivers to consumers in markets across Southeast Asia. Team uses a range of techniques - optimization, machine learning, simulation and reinforcement learning in handling the complexity of allocation (driver to consumer matching) and batching (consumer to consumer matching) of rides and orders across multiple verticals (transport, food, mart, express). Past (and present) appointment: - Capstone advisor for Massachusetts Institute of Technology (MIT) MBAn project: Routing food deliveries under time uncertainty (https://analyticscapstone.squarespace.com/s/Grab_Gabriel_Afriat_Mariana_Suarez.pdf) - Patent Review Board Member at Grab - Data Science Member of Grab-NUS AI Lab (https://ids.nus.edu.sg/Grab-NUS-AI-Lab.html) Notable product launches: - GrabShare wait (https://www.todayonline.com/singapore/grab-offer-cheaper-grabshare-rides-longer-waiting-time-reduce-detours) - Saver option for food deliveries (https://www.grab.com/sg/inside-grab/stories/how-the-saver-option-for-food-deliveries-works/)
Overseas Training Residency at Carnegie Mellon University as part of PhD programme. Collaboration with Professor Kathleen M. Carley, which culminated in two workshops and a conference paper.