Senior Data Scientist

Job Summary

Role: Senior Data Scientist

To lead advanced data science initiatives, develop predictive models, and drive data-driven decision-making by extracting meaningful insights from complex datasets, enabling business growth and innovation.

Key Responsibilities

Key Responsibilities Forecasting & Modeling

• Design and deploy production-grade forecasting solutions using statistical models (ARIMA, ETS, BSTS) and ML approaches (XGBoost, LightGBM, neural networks)

• Engineer sophisticated features: lag features, rolling statistics, external signals, calendar effects, and domain-specific transformations

• Implement forecast reconciliation and hierarchical aggregation for complex business structures

• Establish rigorous evaluation frameworks: backtesting, time series cross-validation, accuracy metrics, prediction intervals, and drift monitoring

Software Engineering & Infrastructure

• Write production-grade Python and R code with modular architecture, comprehensive testing, error handling, and documentation

• Build and maintain sophisticated R Shiny applications with integrated JavaScript components

• Orchestrate ML pipelines using Kubeflow for automated training, validation, deployment, experiment tracking, and model versioning

• Manage infrastructure as code: Databricks workspaces, Azure resources, CI/CD pipelines (GitHub Actions, Azure DevOps), containerization, and secrets management

Analysis, Debugging & Monitoring

• Troubleshoot complex issues across the full stack: data pipeline failures, model degradation, API errors, and integration problems

• Implement continuous monitoring: automated data quality checks, feature drift detection, performance tracking, and alerting systems

• Conduct root cause analysis of forecast errors, identify data anomalies, validate business logic, and communicate findings clearly

Skill Requirements

Required Qualifications Technical Foundation

• Education & Experience: Master's or PhD with 3+ years delivering end-to-end data science solutions in production

• Programming: Strong Python, R and SQL proficiency

• Forecasting Expertise: Time series decomposition, seasonality, trend analysis, ensemble methods, probabilistic forecasting, hierarchical reconciliation

• Data Engineering: Databricks/Spark/Py Spark, Delta Lake, ETL/ELT design, job orchestration, performance tuning

• KNIME: Building analytical workflows, data preprocessing, model pipelines, and system integration

End-to-End Capabilities

• MLOps: Kubeflow pipeline orchestration, experiment tracking, model registry, automated deployment

• Software Engineering: Git workflows, code reviews, testing frameworks (pytest, testthat), modular design, documentation

• Application Development: Build RESTful APIs and R Shiny applications from scratch; handle authentication, deployment, and optimization

• Cloud Infrastructure: Azure services (Databricks, Blob Storage, Data Factory, Key Vault, Functions), container orchestration, CI/CD

Essential Soft Skills

• Autonomy: Self-starter who can take vague requirements and independently drive projects from concept to production

• Problem-Solving: Systematic debugging across the full stack—from source data to infrastructure

• Business Acumen: Translate business needs into technical solutions; understand when "good enough" beats "perfect"

• Communication: Present technical work clearly to non-technical audiences; influence decisions with data; write comprehensive documentation

• Collaboration: Work effectively with cross-functional teams while maintaining end-to-end ownership

Other Requirements

Preferred (Nice-to-have)

• SAP HANA/BW experience, advanced Kubeflow capabilities, Terraform, Kubernetes, PowerBI/Tableau integration, data governance frameworks, multilingual capability