Data Scientist

Own and design streaming and event-driven data pipelines and warehouse models that underpin live operational decisions like ETA, occupancy, dynamic routing, and fraud detection.

Collaborate cross-functionally with product, operations, and business teams to translate open-ended questions into data-driven solutions impacting revenue, margins, and fleet efficiency.

Analyze, validate, and design complex experiments to ensure accuracy and efficacy of models and metrics, exercising critical judgment to override AI outputs when necessary.

Minimum 2 years of combined experience in data science and data engineering roles.

Proficiency with streaming pipeline design and modeling live decision-making metrics such as ETA, occupancy, routing, or fraud.

Strong hands-on skills with advanced SQL (Postgres), Python (pandas, numpy, sklearn), and BI tools for building warehouse models.

Work Location: Mumbai (on-site)

Equally adept at engineering reliable data pipelines and performing rigorous metric validation and modeling.

Experienced in applying classical machine learning, deep learning, or statistical inference to solve complex, open-ended problems in live decision environments.

Comfortable designing and interpreting complex experiments (A/B testing, quasi-experimental, switchback) and integrating business insights into modeling decisions.