Data Scientist T500-21182

About Albertsons Companies Inc.: As a leading food and drug retailer in the United States, Albertsons Companies, Inc. operates over 2,200 stores across 35 states and the District of Columbia. Our well-known banners across the United States, including Albertsons, Safeway, Vons, Jewel-Osco and others, serve more than 36 million U.S customers each week.We build and shape technology solutions that solve customers' problems every day, making things easier for them when they shop with us online or in a store. We have made bold, strategic moves to migrate and modernize our core foundational capabilities, positioning ourselves as the first fully cloud-based grocery tech company in the industry.Our success is built on a one-team approach, driven by the desire to understand and enhance the customer experience. By constantly pushing the boundaries of retail, we are transforming shopping into an experience that is easy, efficient, fun and engaging.About Albertsons Companies India:At Albertsons Companies India, we're not just pushing the boundaries of technology and retail innovation, we're cultivating a space where ideas flourish and careers thrive. Our workplace in India is a vital extension of the Albertsons Companies Inc. workforce and important to the next phase in the company's technology journey to support millions of customers' lives every day. At the Albertsons Companies India, we are raising the bar to grow across Technology & Engineering, AI, Digital and other company functions, and transform a 165-year-old American retailer. At Albertsons Companies India associates collaborate directly with international teams, enhancing decision-making processes and organizational agility through exciting and pivotal projects. Your work will make history and help millions of lives each day come together around the joys of food and inspire their well-being.Position Title: Data ScientistJob Description :Roles & responsibilities: Collaborate with business teams to develop production grade machine learning models on large-scale datasets and improve customers' overall shopping experienceEnhance and apply customer lifetime value models to support various business decision makingGenerate sentiment analysis based on surveys and customer feedbacks in order to deliver lovable customer experiencesIdentify key drivers for customer satisfaction and opportunities to delight customers through mining complex dataApply machine learning to enhance recommendation engines and deliver personalized user experience on ecommerce website and loyalty mobile appBuild models and algorithms to fuel growth initiatives for Digital, Merchandising, Marketing and Loyalty teamsApply predictive modeling techniques to optimize the forecasts for planning needsScale up prototypes and implement reliable automated production workflow for modelsCollaborate with software development engineers to integrate modelsExperience Required : Masters or PhD degree in quantitative discipline: Computer Science, Engineering, Data Science, Math, Statistics or related fields1+ years of industry experience in applying data science and modeling methodologies: regression model, survival model, ensemble modeling, NLP, recommendation algorithm, clustering, deep learning algorithm, experimental design (Multivariate/A-B testing) and nonparametric Bayesian modeling etc.1+ years of experience and proficiency in SQL, Python and/or Spark-ML1+ years of SQL development skills writing queries, transforming data, mining structured and unstructured data.1+ years of hands-on experience in building data science solutions and production-ready systems on big data platforms such as Snowflake, Spark, HadoopStrong teamwork and communication skillAbility to write production-level code in PythonExperience with Snowflake, Azure Databricks is a strong plusSkills Required: Regression modelingsurvival modelingensemble modelingNLPrecommendation algorithmsclusteringdeep learning algorithmsexperimental design (Multivariate/A-B testing)nonparametric Bayesian modelingSQL, Python, Spark-ML, Snowflake, Spark, Hadoop, production-level Python coding