Staff/Sr.Staff Data Scientist - ML & Recommendations

Staff/Sr.Staff Data Scientist - ML & Recommendations

Qualification & Eligibility:

• Bachelor's or higher degree in a quantitative discipline (computer science, statistics, engineering, applied mathematics)

Working Experience:

• Minimum 6+ years of experience
• Startup experience preferred, Edtech work experience bonus

Roles & responsibilities:

• Model Development: Design, train, and deploy recommendation algorithms (collaborative filtering, deep learning, bandits, reinforcement learning, embeddings, etc.).
• Experimentation: Set up A/B testing frameworks, design evaluation metrics (CTR, engagement, retention, revenue lift), and analyze causal impact.
• Data & Feature Engineering: Build and optimize pipelines to generate high-quality features from large-scale user, content, and interaction data.
• Scalability & Systems: Work closely with engineering to ensure models are production-ready, scalable, and low-latency.
• Domain Leadership: Drive innovation in personalization strategies (multi-objective optimization, cold-start solutions, contextual recommendations, etc.).
• Mentorship: Provide technical leadership, code reviews, and best practices to other scientists.

Skill Sets:

• Core ML: Strong background in machine learning fundamentals: supervised/unsupervised learning, regression/classification, probability & statistics.
• Recommendation Systems: Deep understanding of collaborative filtering, matrix factorization, sequence models, embeddings, two-tower retrieval models, deep retrieval/ranking architectures, and multi-task learning.
• Programming: Proficiency in Python (NumPy, pandas, scikit-learn, PyTorch/TensorFlow, JAX). Strong SQL skills.
• Experimentation: Expertise in A/B testing design, statistical significance, confidence intervals, and bias correction.
• Systems/Infra Awareness: Familiarity with model serving, feature stores, online/offline training pipelines, and latency optimization.
• Communication: Ability to translate technical insights into business impact, and influence product/engineering roadmaps.

Good to have:

Experience with big data tools (Spark, Trino, Presto, Hadoop, BigQuery, Redshift).

Leveraging LLMs for personalisation