Senior, Data Scientist

Walmart Walmart · Retail · Bangalore, KA, India

Senior Data Scientist role focused on building and scaling AI/ML systems for international eCommerce personalization at Walmart. The role involves the full ML lifecycle, from feature engineering and model development to deployment and optimization, with a focus on recommendations, search ranking, and customer experience improvement. Requires expertise in real-time systems, experimentation, and recommendation algorithms.

What you'd actually do

  1. Build and scale ecommerce personalization systems: Design, develop, and deploy low-latency ML decisioning and ranking pipelines for critical personalization touchpoints - recommendations, search and browse, homepage, product detail pages, cart, deals, notifications, and lifecycle marketing - leveraging streaming data, online features, and scalable model serving to improve customer relevance at high throughput.
  2. Develop recommendation and ranking models: Build candidate generation, retrieval, ranking, re-ranking, contextual bandit, sequence, uplift, and deep learning models that personalize products, content, offers, and experiences based on customer behavior, intent, context, price, inventory, promotions, and marketplace signals.
  3. Own the full ecommerce personalization ML lifecycle: Lead initiatives end-to-end - from data exploration, feature engineering, model experimentation, offline evaluation, and rigorous A/B testing through production deployment, monitoring, retraining, and continuous optimization across international markets.
  4. Uncover customer intent and personalization opportunities: Work with large-scale clickstream, search, transaction, catalog, content, promotion, inventory, and customer lifecycle data to identify behavioral patterns, unmet customer needs, journey friction, and high-value opportunities for improved relevance, conversion, retention, and incremental business impact.
  5. Drive cross-functional personalization impact: Partner with engineering, product, merchandising, marketing, UX, analytics, and business stakeholders to translate customer and business goals into production-grade ML solutions - communicating model behavior, experiment results, tradeoffs, and recommendations clearly to technical, product, and executive audiences while mentoring other data scientists and raising the quality bar for personalization science.

Skills

Required

  • Python
  • SQL
  • ecommerce personalization
  • recommender systems
  • ranking
  • search relevance
  • customer targeting
  • lifecycle marketing
  • real-time inference
  • streaming platforms (Kafka, Spark Streaming)
  • online/offline feature stores
  • model serving
  • A/B testing
  • causal inference
  • contextual bandits
  • candidate generation
  • embeddings
  • approximate nearest neighbor retrieval
  • learning-to-rank
  • re-ranking
  • sequence modeling
  • model monitoring
  • feature stores
  • drift detection
  • CI/CD
  • governance
  • continuous model delivery

Nice to have

  • LLM-powered analysis and automation workflows

What the JD emphasized

  • Applied ecommerce personalization ML expertise: 6-10 years of hands-on data science experience with a strong focus on ecommerce personalization, recommender systems, ranking, search relevance, customer targeting, lifecycle marketing, or customer growth - ideally in a high-volume, real-time production environment.
  • Real-time systems and scalable ML: Proven experience building low-latency inference, ranking, or decisioning pipelines using streaming platforms (Kafka, Spark Streaming), online/offline feature stores, and production model serving patterns, with a strong grasp of the engineering constraints of personalization at scale.
  • Experimentation, causal inference, and customer impact measurement: Deep experience designing and interpreting A/B tests, holdouts, incrementality studies, uplift models, contextual bandits, or causal inference approaches - with the ability to connect model improvements to customer outcomes and business metrics such as CTR, CVR, GMV, AOV, retention, frequency, and customer satisfaction.
  • Recommendation systems and production ML fundamentals: Proficiency in Python and SQL, with hands-on experience building and productionizing personalization, recommendation, ranking, retrieval, or search relevance models. Strong familiarity with techniques such as candidate generation, embeddings, approximate nearest neighbor retrieval, learning-to-rank, re-ranking, sequence modeling, contextual personalization, and offline/online evaluation, along with production ML practices including model monitoring, feature stores, drift detection, CI/CD, governance, and continuous model delivery.

Other signals

  • personalization systems
  • ML lifecycle
  • real-time inference
  • recommendation models
  • A/B testing