Data Science Intern 212 views

JOB DESCRIPTION

Trust and Safety team at ZaloPay gather highly motivated team players who dedicate in building ZaloPay as the most trusted financial service and best against to bad actors in Vietnam fintech market. By developing and adopting advanced tech-driven prevention mechanisms/solutions while focusing on the user growth and customer experience, we aim to make risk management capability as a core and key differentiation of ZaloPay comparing to other competitors. This helps our business grow sustainably and provide affordable services to all Vietnamese people.

We are looking for a savvy, motivated, team-oriented Data Scientist Intern to join our Risk Data Science team. The team is responsible for bringing insights from data to assess and manage multiple financial risk exposures (e.g., promotion abuse, ATO, KYC fraud, payment fraud), as well as developing and maintaining controls, strategies, solutions, and experiences related to the end-to-end management of these exposures.

The hire will be responsible for the full life-cycle of data product (i.e., from problem identification, to data product design & development, deployment, monitoring & optimization in production) of our Risk Data Solutions & Analytics. Day-to-day duties include data analysis, monitoring and forecasting, creating the logic for and implementing risk rules and strategies; and communicating with stakeholders to ensure we deliver the best possible customer experience while meeting loss rate targets.

RESPONSIBILITIES

The ideal candidate is an experienced solution builder who enjoys optimizing complicated problems or building them from the ground up. The data science team will work closely with our risk pillar owners, data engineers, software engineers on new mechanism/solution initiatives and will ensure optimal data/model/system architecture is consistent throughout ongoing projects. The candidate must be self-directed and comfortable supporting needs of multiple teams, systems and products.

• Focus on bringing statistical depth, analytical insights, and accurate interpretation of data;
• Extract, analyze and apply data-mining/AI/ML techniques to large structured and unstructured datasets;
• Own, design, develop and test large-scale data science pipeline and algorithms that are built for speed, scale and usability;
• Conduct end-to-end data processing, troubleshooting and problem diagnosis in the whole life cycle of AI/ML development and operation;
• Research and investigate academic and industrial AI/ML techniques for product improvements;
• Stay current on published state-of-the-art algorithms and competing technologies;
• Analyze and improve existing data sources, models, strategies and metrics;
• Design and analyze experiments to pilot, test and apply new features & solutions;
• Report, visualize and communicate results & impacts;
• Collaborate with other engineers and team members to evaluate and improve the core components of autonomous systems;
• Identify any product/functionality/technical gaps required to deliver a solution and collaborate with internal teams to define the necessary enhancements to support delivery;
• Evaluate and recommend tools, technologies and processes to ensure the highest quality solutions;
• Foster a culture of ownership, accountability, testing, and measurement; as well as continuous improvement through mentoring, feedback, and metrics.

REQUIREMENTS

A good candidate should possess:

• BSc in machine learning, statistics, math, data science, computer science or other closely related areas;
• Strong machine learning/statistics background with hands-on experience in academia and/or industry, sourcing, cleaning, manipulating and analyzing large volumes of data;
• Willingness to do end-to-end modeling projects emerging from research efforts;
• Willingness to understand a complex system and its various components;
• Great scripting and programming skills (fluent in Python, Java, Scala);
• Experience with open-source machine learning libraries such as scikit-learn, weka, distributed/parallel big data processing architecture (e.g., Hadoop, Spark, MLlib) and deep learning framework (e.g., TensorFlow, Pytorch);
• Good problem-solving and communication skills;
• Ability to work well in a fast-paced culture and ability to manage multiple projects and deadlines.