Advanced Data Scientist

Responsibilities

• Design,optimize, andmaintainscalable ETL pipelines usingPySparkand Databricks on cloud platforms (Azure/GCP).

• Develop automated data validation processto proactivelyperform data quality checks.

• EmploykeyDatabricksmodules(DeltaLiveTables, Unity Catalog,MLFlow)tofacilitatecreating,running experiments,automating,and scheduling jobs on Databricks.

• Optimizetheallocation of cloud resourcesand Databricks DBUstomanage and controlcloudand Databricks consumptioncost.

• EmployGitHubrepositoriestoensure thatproduction code managementbest practices are beingstrictly adhered to.

• Build and tuneML/AI and optimizationmodels,identifyalgorithmic performanceimprovement opportunities, and perform experiments todemonstrateincrementalvaluedelivered.

• Havefrequent conversations withBusinessStakeholders tounderstand theirrequirementsandconcerns.Explaindata deficiencies,model performance/root cause analysis, andmodel output.

• Follow best practices inDataArchitecture, Coding, andProject Managementoperations.

• Collaborate with cross-functional teams, such asCustomers’Stakeholders, Engagement Managers, Data Ops/Job Monitoring, ProductManagement& Software Engineering.

• Expandtheuseof analytics, ML/AI,mathematical optimization,Gen-AI/LLMs and Agentic-AI in the context of Retail/CPGbusinessuse casessuch asanomaly detection,demand forecasting, price elasticity modeling,promotionsfeatures & strategy simulation, productcannibalization and halo modeling, markdownoptimization,product allocation, reorder/replenishment,size and pack optimization,workforce scheduling & task optimization

Qualifications

Job Requirements:

• Minimum Education:

• Master’sdegree inengineering,computer science, data science, operations research, statistics, mathematics, quantitativesciencesor relevant work experience

• Minimum Work Experience (years):

• 6+ years of experiencein Data Science/Data Engineeringwith emphasis on the full lifecycle of Data Science-ML/AI projects.

• Within thattimeframe, experience is expected in: Python/PySpark, SQL, and relational or NoSQL databases, and cloud resource management.

• Key Skills and Competencies:

• Experience working with AWS, Azure, or GCP cloud environments.

• Experienceimplementingadvanced analytics, ML/AIalgorithms (suchas: ,

• StatisticalTimeSeries:Exponential Smoothing Models,S/ARIMA;

• MachineLearning: Random Forests,Gradient Boosting Methods;

• Neural Networks:TiDE(Google),DenseNet& Prophet(FB-Meta);

• Foundational Time Series Models:TimesFM(Google), Chronos(AWS)

• Mathematical (constrained linear,non-linearand network) optimization models

• Provenexperience buildingend-to-endproductiongrade Data & ML/AIpipelinesusingPySpark, Python (Pandas/NumPy)and SQL.

• Experience working with Git (or similar code management repositories) as a collaboration tool. production-grade

• Experience with orchestration tools likeDatabricks, Airflow (or similar tools like Snowflake,Dagster, etc.).

• Understanding ofRetail/CPGindustrybusiness challengeswith an emphasis on Supply Chain, Pricing/Promotions/Markdowns,Inventory Allocation, Assortment Mix Planning,Size & Pack Optimization,Retail Shrink/Fraud & Anomaly Detection,and Workforce optimization applicationsarehighly desirable.

• Excellent verbal and written communication skills, especiallyas it relates totechnical communications.Ability to present technical analysis to business stakeholders.

• Demonstrated ability to learnnew technologiesquickly and independently, particularly as technology in this domain rapidly advances.In this context, a working knowledge of GenAI/LLMs, Agentic-AI and related frameworks (e.g.LangChain) will be a plus.

• Ability to workindependently with minimal supervisionand achieve stretch goals in a highly innovative and a fast-paced environment.