About the team + role Insights from data power most decisions at Robinhood and our company trajectory is defined by the systems, tools, and analytics powered by this exceptional team. As a Machine Learning Engineer working on Fraud and Risk, you would work with backend engineers, product managers and operations teams across the company to understand and mitigate the risks to our business.
Robinhood faces unique data challenges with a focus on integrating complex data streams such as rapidly changing market data, user data based on app activity, and brokerage operations data to understand user behaviour and the risks to our business.
We are looking for a Machine Learning Engineer to help detect and reduce risk to Robinhood - a crucial role to our business and customers. The ideal candidate is passionate about understanding the different fraud vectors at a fast-growing company and building solutions to mitigate these risks. This team is part of the larger Data Team here at Robinhood.
What you'll do Combining knowledge of several research domains to improve our understanding of different risks to Robinhood and help power decisions. Designing new machine learning systems to power the fraud prevention and risk reduction efforts at Robinhood especially in product areas. Build production grade models on large-scale datasets to measure effectiveness across products by leveraging statistical modeling, machine learning and data mining techniques. Collaborate with the rest of the data team and partner marketing, product, content, design teams to build data solutions and products to drive user and revenue growth. Work with cross-functional teams to implement insights and analytical solutions to empower data-driven decision making. Problem solving skills and a can-do attitude to dive deep into data to solve business problems. What you bring Familiarity with fraud domains and banking processes, including account takeover, ACH fraud, debit/credit card fraud, first-party fraud, and synthetic identity fraud. Demonstrated expertise in building and deploying fraud models using large datasets, with a strong track record of success in fraud detection and prevention. Knowledge of model risk governance and experience collaborating with model validation teams to ensure compliance with regulatory requirements. Graduate degree in a quantitative field such as mathematics, economics, statistics, engineering or natural sciences (or equivalent research experience). Solid understanding of unsupervised learning, statistical analysis and machine learning algorithms for imbalanced datasets. Excellent programming skills, including familiarity with either Python (numpy, scipy, pandas) or R programming languages. Experience with Tableau, Looker, and/or Mode. Experience communicating data driven insights. 2+ years professional experience as a Machine Learning Engineer. 1 year of experience working in a research setting in academic or commercial setting. Passion for working and learning in a fast-growing company. Strong customer empathy. Intense sense of curiosity.
#J-18808-Ljbffr