Data Scientist

- Advanced Modeling & Timeseries Forecasting: Design, train, and implement robust Machine Learning (LightGBM, XGBoost) and Deep Learning (PyTorch) models specifically focused on complex demand sensing and resolving cold-start forecasting problems. - Feature Engineering Pipelines: Build and optimize scalable data pipelines leveraging a hybrid SQL/Python architecture (dbt, Snowflake) to extract rich, localized temporal signals from high-volume transactional retail data. - End-to-End Deployment (MLOps): Partner with our engineers to transition your models from prototype into scalable, monitored, and reliable production pipelines using tools like MLflow and Optuna.

- Strong predictive modeling foundation: Extensive experience with traditional ML algorithms, Deep Learning frameworks, and complex time-series forecasting. - Experience developing production-grade Python code: High proficiency in Python, Pandas, and modern software practices (testing, clean code, code review, CI/CD). - Data & Pipeline Expertise: Hands-on experience optimizing data models and access patterns for modern data warehouses (Snowflake, Databricks) utilizing SQL and transformation tools like dbt.

- Experience developing production-grade Python code: High proficiency in Python, Pandas, and modern software practices (testing, clean code, code review, CI/CD). - Data & Pipeline Expertise: Hands-on experience optimizing data models and access patterns for modern data warehouses (Snowflake, Databricks) utilizing SQL and transformation tools like dbt. - Cloud & Data Infrastructure: Experience working with scalable cloud infrastructure (AWS, GCP, or Azure), and handling columnar data formats like Parquet.

- Data & Pipeline Expertise: Hands-on experience optimizing data models and access patterns for modern data warehouses (Snowflake, Databricks) utilizing SQL and transformation tools like dbt. - Cloud & Data Infrastructure: Experience working with scalable cloud infrastructure (AWS, GCP, or Azure), and handling columnar data formats like Parquet. - MLOps Exposure: Experience with tools and frameworks for training, tracking, deploying, and monitoring models in production (e.g., MLflow, Optuna, Prefect, or Airflow).

- Feature Engineering Pipelines: Build and optimize scalable data pipelines leveraging a hybrid SQL/Python architecture (dbt, Snowflake) to extract rich, localized temporal signals from high-volume transactional retail data. - End-to-End Deployment (MLOps): Partner with our engineers to transition your models from prototype into scalable, monitored, and reliable production pipelines using tools like MLflow and Optuna. Your Skills

- Cloud & Data Infrastructure: Experience working with scalable cloud infrastructure (AWS, GCP, or Azure), and handling columnar data formats like Parquet. - MLOps Exposure: Experience with tools and frameworks for training, tracking, deploying, and monitoring models in production (e.g., MLflow, Optuna, Prefect, or Airflow). Desirable

- Analytic Engine Development: Design and develop scalable functional analytic capabilities that seamlessly integrate into Anaplan Applications, translating raw customer data into automated, high-value business insights. - Advanced Modeling & Timeseries Forecasting: Design, train, and implement robust Machine Learning (LightGBM, XGBoost) and Deep Learning (PyTorch) models specifically focused on complex demand sensing and resolving cold-start forecasting problems. - Feature Engineering Pipelines: Build and optimize scalable data pipelines leveraging a hybrid SQL/Python architecture (dbt, Snowflake) to extract rich, localized temporal signals from high-volume transactional retail data.