Role : Senior Data Scientist

Experience : 3 to 5 Years (strictly relevant experience only)

Location : Bangalore (Hybrid /Remote)

Notice Period : 30 Days

About the Role :

You will design and own large-scale personalization and recommendation systems responsible for deciding which products to show, to whom, and at what time while balancing multiple business constraints and optimization goals.

The role focuses on building intelligent recommendation engines, ranking systems, and real-time personalization solutions for large-scale e-commerce platforms.

Key Responsibilities :

- Designed and developed end-to-end recommender systems for large-scale e-commerce personalization platforms.

- Built candidate generation systems using retrieval models, embeddings, ANN (Approximate Nearest Neighbor) search, and vector-based recommendation techniques.

- Developed ranking and re-ranking models using GBDT, Deep Learning, and hybrid recommendation approaches.

- Designed objective functions aligned with business KPIs including conversion rate (CVR), revenue optimization, customer engagement, and profit margin improvements.

- Built intelligent decision systems using multi-objective optimization and business constraint-based recommendation frameworks.

- Implemented and analyzed online experimentation frameworks including A/B testing and multi-armed bandit algorithms.

- Developed scalable feature engineering pipelines including user embeddings, sequence modeling features, behavioral signals, and contextual recommendation features.

- Built near real-time personalization systems to transition from traditional batch recommendation architectures.

- Worked on multi-objective optimization problems balancing recommendation relevance, inventory availability, revenue goals, and product margins.

- Handled cold-start recommendation problems and sparse user behavior scenarios using hybrid and embedding-based recommendation techniques.

- Developed scalable machine learning pipelines using Python and SQL for recommendation and personalization workflows.

- Built ML models using TensorFlow, PyTorch, XGBoost, and LightGBM for recommendation and ranking systems.

- Developed and optimized feature stores and batch/streaming pipelines for real-time personalization systems.

- Worked extensively on recommendation retrieval architectures, ranking pipelines, and AI-driven personalization systems.

- Designed scalable experimentation frameworks to measure recommendation quality, customer engagement, and business impact.

- Applied causal inference and experimentation methodologies to improve personalization system performance and decision-making accuracy.

- Collaborated with product, engineering, analytics, and business teams to align recommendation systems with customer and business goals.

- Formalized complex business problems into machine learning models and optimization frameworks for intelligent personalization systems.

- Optimized recommendation latency, scalability, and relevance for high-traffic e-commerce platforms.

- Continuously improved recommendation quality and personalization accuracy using AI/ML-driven optimization strategies and real-time behavioral analytics