Join a team focused on advancing demand forecasting capabilities that support digital fulfillment operations and help improve planning across multiple channels. This remote opportunity is ideal for a strong Python and ML engineering professional who enjoys scaling data science work into reliable, production-ready systems.

Responsibilities

• Build and maintain machine learning pipelines that support forecasting workflows from data preparation through deployment
• Scale pandas-based processes into PySpark and other distributed frameworks for large-volume processing
• Develop and optimize data pipelines with an emphasis on performance, reliability, and cost efficiency
• Support model training, validation, experimentation, and versioned deployment in production environments
• Work with analytical data stores and manage dataset design, partitioning, clustering, and validation practices
• Contribute to workflow orchestration using tools such as Kubeflow Pipelines, Vertex AI, or Airflow
• Collaborate with data scientists and platform engineers to productionize forecasting solutions
• Refactor, extend, and improve existing codebases while following sound software engineering practices
• Support CI/CD, testing, dependency management, and code quality processes for ML systems
• Help modernize forecasting infrastructure used to support store operations planning and customer experience

Skills

• Strong Python programming skills with experience writing production-quality code
• Hands-on machine learning and data science experience, including building and deploying ML models
• Experience with time series forecasting methods such as Prophet, ARIMA, or similar approaches
• Ability to convert pandas workflows to PySpark for large-scale data processing
• Experience with distributed data processing tools such as Spark, Dask, or Ray
• Knowledge of hyperparameter tuning, model validation, and experiment tracking
• Familiarity with feature engineering and feature store concepts
• Experience with BigQuery or similar analytical databases
• Working knowledge of Git, testing frameworks such as pytest, and code quality tools
• Understanding of cloud platforms such as GCP, including storage and ML services
• Experience with Docker, Kubernetes, and CI/CD workflows

Preferred Skills

• Experience with Ray for distributed training or inference
• Exposure to Hadoop ecosystem tools such as Hive or HDFS
• Knowledge of model monitoring and drift detection practices
• Familiarity with infrastructure-as-code tools such as Terraform
• Background in retail, supply chain, or demand forecasting environments
• Experience helping data science teams turn research code into scalable production solutions
• Comfort working in a collaborative, cross-functional environment
• Strong problem-solving skills and a continuous improvement mindset

Horizontal is committed to fostering an inclusive environment where different perspectives, backgrounds, and experiences are valued. We welcome candidates who bring curiosity, collaboration, and a shared commitment to building equitable and respectful workplaces.