- Participate in the credit scoring project as a member to create credit scoring model and to work with data engineers to create machine learning pipeline that is available for real-time operations.
- Research and apply relevant ML & DL frameworks that help solve business problems such as: customer segmentation, customer churn, product recommendation and so on.
- Lead ML & DL component of data capturing projects that help automate data input process from images to reduce operational time for tellers.
- Create various NLP models that help automate tasks in the company’s chat system.
- Participate in designing features for Customer View project.
- Train fellow data analysts on basic machine learning frameworks and statistical methodologies that are relevant for statistical and scientific methods of evaluation hypothesis.
- Identify and encourage areas of growth and improvement within the team
- Willing to explore new tools and skillsets in the market or industries to apply to the team and the company.
- 3+ years experiences as a data scientist
- Strong ability in framing business problems into machine learning problems to derive relevant solutions.
- 3+ year experience with data science languages such as Python, R or Julia as well as CI version control such as GitHub or GitLab.
- Fluent use of ML frameworks such as scikit-learn, xgboost/lightgbm/catboost and have experience with one of the DL frameworks such as: PyTorch, fastai, Tensorflow/Keras, MXNet.
- Experience with building data pipeline, training model and inferencing on contaminated environment such as Docker or integrating ML models with APIs for real-time prediction.
- Good demonstration of communication and presentation skills, know when and how to use what sort of tools to deliver results to business teams.
- Experience with AWS cloud ecosystem such as S3, RedShift, Lambda, EC2.
- Degree in data-centric disciplines: data science, computer science, economics, statistics, …