Principal Data Analyst, Information Retrieval

As a Senior Data Scientist, you will be responsible for working on the core ranking and retrieval systems behind search to optimize how user queries map to the product catalog at scale. Key Responsibilities: - Develop search ranking models including learning-to-rank, neural ranking, and hybrid models. - Improve query understanding through tokenization, normalization, and semantic matching. - Utilize embeddings such as dual encoders and semantic search. - Work with implicit feedback signals like click models, dwell time, and conversions. - Design and evaluate ranking metrics such as NDCG, MAP, CTR, and CVR. - Conduct controlled experiments to enhance relevance. Qualifications Required: - Experience in search, ranking, or information retrieval. - Strong feature engineering and modeling skills. - Understanding of trade-offs between offline metrics and online impact. - Product intuition related to search UX. - Preferable experience in recommender systems or ranking problems. In terms of technologies, the indicative tech stack includes Python, SQL, Elasticsearch/OpenSearch or similar technologies, and ML frameworks like XGBoost, LightGBM, and deep learning models. If you are looking for a challenging role where you can contribute to improving search relevance, handling long-tail queries, and balancing relevance with business objectives, this opportunity is ideal for you. As a Senior Data Scientist, you will be responsible for working on the core ranking and retrieval systems behind search to optimize how user queries map to the product catalog at scale. Key Responsibilities: - Develop search ranking models including learning-to-rank, neural ranking, and hybrid models. - Improve query understanding through tokenization, normalization, and semantic matching. - Utilize embeddings such as dual encoders and semantic search. - Work with implicit feedback signals like click models, dwell time, and conversions. - Design and evaluate ranking metrics such as NDCG, MAP, CTR, and CVR. - Conduct controlled experiments to enhance relevance. Qualifications Required: - Experience in search, ranking, or information retrieval. - Strong feature engineering and modeling skills. - Understanding of trade-offs between offline metrics and online impact. - Product intuition related to search UX. - Preferable experience in recommender systems or ranking problems. In terms of technologies, the indicative tech stack includes Python, SQL, Elasticsearch/OpenSearch or similar technologies, and ML frameworks like XGBoost, LightGBM, and deep learning models. If you are looking for a challenging role where you can contribute to improving search relevance, handling long-tail queries, and balancing relevance with business objectives, this opportunity is ideal for you.