Get to know our Team:
The Grab Financial Risk team acts as guardians of risk for all financial products within Grab. The data team is dedicated to data driven risk solutions, leverages our rich datasets to solve problems ranging from payment risk to money laundering. We’re a hands on team working on the end to end data lifecycle: from wrangling data to understanding the tradeoffs between model complexity and deployment in production.
Our objective is to provide the best user experience through innovation. If you’re passionate about solving complex problems with immediate real-world impact, we want you!
Get to know the role:
Develop a deep behavioural understanding and intuition of our users from data to identify emerging fraud trends, develop, and improve machine learning models to detect risk and fraud.
Collaborate with various functions to manage the entire end-to-end life cycle of designing, implementing, and deployment of models.
Work independently or in a team to solve complex problem statements
Think out of the box and innovate in all possible perspectives.
The must haves:
Ph.D. or Master’s in Computer Science, Electrical/Computer Engineering, Industrial & Systems Engineering, Mathematics/Statistics, or related technical disciplines.
Proficient in programming in languages like Python, R, Java, or C++.
Proficient in algorithm design given various data structures including sparse matrices, sequences, trees, and graphs.
Strong working knowledge of machine learning including classification, clustering, and anomaly detection.
Experience in ETL, feature selections, hyper-parameter optimization, model validation and visualization.
Experience in tools like Scikit-Learn, Pandas, and XGBoost.
Experience in deep learning frameworks like Tensorflow or PyTorch.
Deep understanding and implementation experience of predictive modeling algorithms such as logistic regression, neural networks, forward propagation, decision trees and heuristic models, with familiarity dealing with trade-offs.
Experience in interfacing with other teams and departments to deliver impact solutions for the organization.
Self-motivated, independent learner, and enjoy sharing knowledge with team members.
Detail-oriented and efficient time manager in a dynamic and fast-paced working environment.
Really nice to haves:
Deep understanding of the fraud space with hands-on knowledge of fraud, payments and risk, especially on tech products.
Recent programming experience in a production environment.
Worked with geospatial databases or graph databases.
Solid understanding of model interpretability.
Experience with RNN/LSTM or Graph Neural Network.