Position : Senior Data Scientist

Experience : 3-5 Years

Work Mode : WFO Hybrid 2 days in a week.

Job Location : Bangalore

Job Type : Full Time

About the Role :

We are looking for a Senior Data Scientist to join the Search Squad and work on the core search, retrieval, and ranking systems that power product discovery at scale.

You will be responsible for improving how user queries are understood, how relevant products are retrieved, and how search results are ranked to deliver better relevance, user experience, and business outcomes.

Key Responsibilities :

Develop and optimize Search Ranking Models, including :

- Learning-to-Rank (LTR)

- Neural Ranking

- Hybrid Ranking

Build and enhance Query Understanding capabilities :

- Tokenization and normalization

- Semantic matching

- Query intent understanding

- Query expansion

Develop Semantic Search and Retrieval solutions using :

- Embeddings

- Dual Encoders

- Vector Search

-Hybrid Search

Leverage implicit user feedback signals such as :

- Click-through rate (CTR)

- Dwell time

- Add-to-cart activity

- Conversions (CVR)

- Design and optimize ranking features using user, query, and product-level signals.

Evaluate search relevance using metrics such as :

- NDCG

- MAP

- Precision / Recall

- CTR / CVR

- Design and execute A/B tests and controlled experiments to measure improvements in search relevance and business impact.

- Analyze the trade-offs between offline ML metrics and online product/business metrics.

- Work on improving search for long-tail queries, ambiguous intent, and complex user searches.

- Collaborate closely with Data Engineers, ML Engineers, Product Managers, and Search Engineers to productionize models.

- Current Search Challenges

- Moving from traditional lexical search to semantic retrieval.

- Improving relevance for long-tail and low-frequency queries.

- Handling ambiguous search intent.

- Combining lexical + semantic/hybrid search approaches.

- Balancing search relevance, user experience, and business objectives.

- Improving ranking quality while maintaining low latency and scalability.

Required Technical Skills :

Must Have :

- Strong experience in Python and SQL.

- Hands-on experience in Machine Learning and Feature Engineering.

- Strong understanding of Search, Ranking, or Information Retrieval.

- Experience with Learning-to-Rank / Ranking Models.

- Experience with Elasticsearch, OpenSearch, Solr, or similar search technologies.

- Strong understanding of Semantic Search, Embeddings, and Vector Search.

- Knowledge of ranking/relevance metrics such as NDCG, MAP, CTR, and CVR.

- Experience with A/B testing and experimentation.

- Experience with ML frameworks such as XGBoost, LightGBM, or Deep Learning frameworks.

Good to Have :

- Experience with NLP and Transformer-based models.

- Experience with Dual Encoder architectures.

- Experience with BM25 and Hybrid Search.

- Experience with Click Models / user behavior modeling.

- Experience working on e-commerce, product search, recommendation, marketplace, or large-scale search platforms.

- Understanding of search UX and product relevance.

- Experience deploying and monitoring ML models in production.