About the Project
build and optimize end-to-end personalization systems, refining scoring, ranking, and eligibility models; the role emphasizes robust experimentation, model monitoring, and alignment with lifecycle-based objectives, leveraging advanced ML and data insights to address cold starts, data drift, and explainable outcomes.
About the Team
We own the end-to-end user journey—from first app launch to daily habit loops—across Search, Personalization, Watch Experience, Interactivity, and more. We blend world-class engineering, ML, design, and data to deliver a seamless, personalized, and engaging OTT experience at massive scale.
Duties & Responsibilities
· Analyze large-scale user behavior and content metadata to uncover actionable insights and build impactful personalization models.
· Design, develop, and deploy ML models including collaborative filtering, content-based recommendations, sequence models, and retrieval-ranking pipelines.
· Integrate models into production systems ensuring low-latency, high-accuracy performance at scale.
· Collaborate with engineers, product managers, designers, and data scientists to define personalization goals and drive feature impact across user journeys.
· Develop robust A/B test frameworks, analyze experiments, and drive iteration based on performance and user engagement.
· Actively monitor model performance, detect data drift, and refine strategies to improve long-term personalization quality.
· Leverage LLMs and embeddings to improve personalization for underrepresented content, new users, and diverse formats.
· Present technical strategies and results to cross-functional stakeholders and leadership.
Qualifications
· Bachelors/Masters in Data Science, Statistics, Computer Science, Mathematics, or a related field with 8-10 years of experience in data science.
· Proven experience in data science and machine learning, preferably in personalization or recommendation systems.
· Strong proficiency in Python, SQL, and relevant data science libraries (Pandas, Scikit-learn, TensorFlow, PyTorch, etc.)
· Expertise in building and deploying machine learning models into production systems.
· Experience with big data technologies (e.g., Hadoop, Spark) and cloud platforms (e.g., AWS, Google Cloud).
· Deep understanding of statistical analysis, machine learning, data mining, and predictive modeling techniques.
· Should be comfortable leveraging LLMs and internals.
· Strong problem-solving skills with the ability to translate business problems into data science solutions.
· Excellent verbal and written communication skills, with the ability to present complex information to non-technical stakeholders.
