Senior Data Scientist

Role: Senior Data Scientist

Function: Data Science / Machine Learning

Location: Delhi

Type: Full-time

Industry: Media Production, Broadcast Media, Online Media

About Company

One of India's largest private FM radio networks, reaching 40 million+ listeners weekly. The company broadcasts across 49 cities, 1,000+ towns, and 50,000 villages.

It is the only private FM station broadcasting from Jammu & Kashmir, with an international presence in Singapore and Bhutan. Its digital platform extends the brand into curated lifestyle, music, and news content.

The company operates at the intersection of legacy broadcast media and digital innovation, with a team of 740.

Position Overview

The company is building a next-generation media super-app that unifies video, audio, radio, micro-drama, news, and commerce on a single digital platform. This is a senior individual contributor role responsible for driving the data science behind content discovery, personalization, ranking, and audience intelligence at scale. The right candidate takes full ownership of ML systems — from problem framing and experimentation through to production deployment and ongoing model performance.

• Role & Responsibilities
• Own the full ML lifecycle for recommendation, personalization, content ranking, and search — from problem definition and feature design through model training, evaluation, and production deployment.
• Develop and iterate on models using behavioural, engagement, and content metadata signals across video, audio, and commerce surfaces.
• Design and build feature pipelines and reusable feature sets for ML training and inference, collaborating with data engineering on upstream data quality and availability.
• Run structured experiments (A/B tests, interleaving) to measure model impact on engagement, retention, and discovery metrics; translate results into product decisions.
• Enable continuous model improvement by designing feedback loops that capture live user interactions for retraining and evaluation.
• Explore and apply AI techniques across use cases including semantic search, content classification, audience profiling, content moderation, and generative AI-powered media experiences.
• Partner with product and engineering teams to translate business problems into well-scoped ML solutions and communicate findings to non-technical stakeholders.

Must Have Criteria

• 7–12 years of hands-on data science or applied ML experience, with a track record of shipping models into production on consumer-scale platforms.
• Demonstrated end-to-end ownership of ML pipelines — from data preparation and feature engineering through model training, evaluation, and production deployment.
• Strong proficiency in Python for model development, experimentation, and data analysis.
• Deep experience building and evaluating models for recommendation, personalization, ranking, or search systems.
• Hands-on experience with ML experimentation frameworks and A/B testing at scale.
• Experience working with large-scale behavioural and event-streaming datasets to derive features and training signals.
• Demonstrated ability to deploy ML models into production on AWS, GCP, or Azure, including monitoring model performance post-launch.

Nice to Have

• Background in media, OTT, video, audio, music, social media, gaming, or news platforms.
• Exposure to Generative AI, LLMs, vector databases, or embedding-based retrieval systems.
• Familiarity with feature stores and MLOps tooling for managing model and feature lifecycle.
• Experience with NLP, speech, or audio/video understanding models.

What We Offer

• End-to-end IC ownership of ML models serving tens of millions of users across a greenfield media super-app.
• Opportunity to work at the convergence of broadcast media and digital innovation, with direct influence on product direction.
• Collaborative environment with engineering, product, and analytics teams tackling high-impact personalization and content intelligence problems.