Data Scientist

Key Skills

Java Programming, Python Programming, C++, C Programming, SQL, Cloud computing, Scala Programming, Machine learning techniques, Data science techniques, MATLAB Programming, PyTorch, TensorFlow, R Programming

Job Description

Are you a master of data science? Are you looking for an opportunity to contribute your creative mindset and energy to the growth and success of a hyper-growth, pre-IPO product?

The Data Scientist's primary responsibility is contributing to GeoComply’s success by ensuring continuous development and improvement of AI-based Anti-Fraud systems. The ideal candidate for this role is a person with strong analytical skills, detail-oriented, proactive, and able to work in a dynamic environment. We expect that the Data Scientist has experience working with complex datasets, building models, and distilling insights for management. You enjoy working in collaborative teams and have excellent interpersonal skills. The Data Scientist should take responsibility and always see a path forward to success. It will be a plus if you have experience working in short, iterative development cycles and have a great passion for working in fast-paced development process environments.

You will have an opportunity to work with an international team, with colleagues in Canada, the US, and Vietnam. This role will report to the Data Science Lead, and you will work closely with Data Science, Data Analytics, Reporting, Development, and Business teams. In addition, you will have the opportunity to influence the development plan directly, research, and develop your ideas for the product.

What You Will Be Doing

• Design, build and maintain ML/DL models for Geofence and Anti-fraud management systems;
• Develop and strengthen ML/DL models to solve anomalies detection problems;
• Perform EDA process, feature engineering and work on developing models to detect suspicious signs;
• Correctly frames a problem and comes up with a hypothesis;
• Assesses the effectiveness and develop practical ML/DS solutions on an ongoing basis;
• Identifies new data that could enhance the quality and accuracy of models to improve detection;
• Improve current anti-fraud features on both client and server sides;
• Create structured and reliable documentation;
• Write structured, well documented and tested code for the deployment;
• Support and help with clients' requests;
• Collaborate with the Reporting, and Data Analytics Teams in Vietnam;
• Collaborate with a client’s Anti-Fraud Teams and work on developing non-geolocation anti-fraud solutions;
• Follow best practices and processes established by the team;
• Develop and maintain a thorough understanding of the company’s technologies, processes and teams.

About You

• At least 2 years of work experience with machine learning and data science;
• Education or training in a relevant field(ex. Data Science, Statistics, Mathematics, Computer Science);
• Strong Python knowledge and the associated data analytics/machine learning packages (NumPy, pandas, scikit-learn, scipy, etc.);
• Experience with deep learning frameworks(PyTorch, TensorFlow, MXNet, etc.)
• Strong background working with predictive and statistical modelling, machine learning and strong expertise in all phases of the modelling pipeline;
• Strong background with EDA process and feature engineering;
• Understanding of databases and network technologies. Relational databases such as MySQL;
• Advanced knowledge of maths and statistics;
• Intermediate to advanced proficiency in English (both verbal and written), with the ability to effectively communicate complex information in a simple manner;
• Strong interpersonal skills with the ability to communicate and build relationships with internal and external stakeholders;
• Highly organized and detail-oriented;
• Ability to prepare reports and visualizations;
• Strong ability to operate independently and make clear and thoughtful decisions.

Bonus Points if You

• Experience in cloud technologies (AWS preferred);
• Experience in risk management and fraud detection;
• Experience working with distributed data processing frameworks such as Spark and Delta Lake.