Sr. Data Scientist

Home Credit Indonesia; Jakarta Pusat; On-site; IDR 300,000,000 - 540,000,000; Full time

Job summary

Home Credit Indonesia is seeking a senior data scientist to develop and deploy predictive models focusing on big data and scoring. You will build, monitor, and refine models used across internal teams and external partners, deploying them in a real-time decision engine using Python.

The role requires strong analytics expertise, 5+ years in modelling, and excellent English communication. Collaboration in an agile environment is essential.

Qualifications

• Minimum 5 years in a modelling/data science team.
• Proficient with Python for data science and ML libraries.
• Strong in predictive modelling and statistics.
• English fluency in writing and speaking.

Responsibilities

• Build machine learning models and monitor results for internal departments and partners.
• Deploy predictors in Real Time Decision Engine (Python based).
• Share knowledge and act as expert consultant for Big Data and Scoring.

Education

Bachelor's or Master's degree in Statistics / IT / Applied Mathematics / Physics / Engineering or quantitative fields

Tools

Python (scikit-learn, xgboost, lightgbm)

PySpark

Power BI

Apache Airflow

Git

SQL

Job description

In this role, you will work with large amount of data and information and provide other departments with modelling, advance analytics, and automation support with focus on Big Data and Scoring.

Key responsibilities:

• Build machine learning model and monitor the result for various internal departments and external partners.
• Deploy predictors or machine learning model in Real Time Decision Engine (Python based).
• Knowledge sharing with teammates and be expert consultant for assigned area of knowledge. The assigned area will be connected to Big data and Scoring.

We welcome talents with these qualities:

• Bachelor's or Master's degree, majoring in Statistics, IT, Applied Mathematics, Physics, Engineering or equivalent and/or quantitative fields (eg. algebra, probability theory, operational research, machine learning).
• Minimum 5 years in a modelling/data science team.
• Proficient with Python for data science (scikit-learn, xgboost, lgbm, etc.), PySpark, Power BI, Apache Airflow, Git, and SQL queries.
• Have a solid understanding of predictive model using both statistical (classical) and machine learning models.
• Familiar with risk credit scoring, NLP, and hadoop ecosystem will be an advantage.
• Adaptable to work in a dynamic and agile environment.
• Excellent communication in English, both written and spoken.