Data Scientist

About Setu

At Setu, we believe that every company can become a fintech company. Any tech-enabled business that wants to offer or build financial products can consume Setu APIs.

Our Data Science team is working on understanding the financial behaviour of 1.4 billion Indians across a broad spectrum of fintech sectors—including personal lending, collections, personal finance management (PFM), and BBPS.

We are not just a team; we are building the intelligence layer for the future of fintech.

About the Role

As a Data Scientist I/II with 2–4 years of experience, you will explore, experiment, and build critical, scalable, and high-value data science solutions. You will work closely with business and engineering teams in Bengaluru / Bangalore to solve challenging problems while working on data that can directly influence financial products.

We are constantly pushing the boundaries of data science across Computer Vision, Tabular Data, NLP, Generative AI, Credit Risk, Alternate Data, and Financial transaction intelligence. For example, our Sesame model understands bank transactions with state-of-the-art accuracy.

What you will do:

• Translate business problems into data science and machine learning solutions.
• Explore large, complex datasets to identify meaningful patterns.
• Build, validate, and iterate on ML models using Python/PySpark.
• Work on model deployment and contribute to production-grade systems.
• Collaborate with product, engineering, and business teams to take models from ideation to production.

We are looking for someone who is passionate about Setu's mission, demonstrates strong ownership, creates value for customers, strives for excellence, manages time effectively, adapts quickly, and can independently manage the full ML lifecycle from problem understanding through deployment.

To excel in this role:

• Bachelor's or Master's degree in Engineering.
• 2+ years of experience in Data Science / Machine Learning.
• Prior experience with BBPS data exploration, Alternate data credit risk models, Bank statement / financial transaction data, Relevant fintech use cases.
• Strong understanding of Statistics, Hypothesis testing, Statistical inference, Simulations, Optimization, and ML techniques (Random Forest, XGBoost, MLP, SVM).
• Hands-on experience deploying models to production using Python/PySpark with strong feature engineering skills.