We are seeking a Development Engineer to help modernize and scale demand forecasting capabilities within a digital fulfillment environment. This role offers the opportunity to work at the intersection of machine learning, data engineering, and software development to support forecasting solutions that improve operational planning and customer experience.

Responsibilities

• Develop and enhance machine learning pipelines that support forecasting for order volumes, units, and fulfillment capacity across multiple channels.
• Collaborate with data scientists and platform engineers to move research concepts into reliable production workflows.
• Convert and optimize pandas-based processing into scalable PySpark solutions for large data workloads.
• Build and maintain data pipelines that are efficient, dependable, and designed for cost-effective performance.
• Support pipeline orchestration using tools such as Kubeflow Pipelines, Vertex AI, or Airflow.
• Integrate data validation, training, and deployment steps into end-to-end ML workflows.
• Work with analytical databases and cloud storage platforms to design, write, validate, and organize datasets effectively.
• Refactor and extend existing Python codebases with strong testing and code quality practices.
• Contribute to modernizing forecasting systems that help improve store operations planning and service outcomes.

Skills

• Hands-on experience building and deploying machine learning models in production environments.
• Practical time series forecasting experience using tools or approaches such as Prophet, ARIMA, or similar methods.
• Strong understanding of feature engineering, model validation, hyperparameter tuning, and experiment tracking.
• Experience translating pandas workflows into PySpark for scalable processing.
• Working knowledge of distributed processing frameworks such as Spark, Dask, or Ray.
• Experience with BigQuery or comparable analytical databases, including table design and dataset validation.
• Proficiency in Python and experience writing production-quality code.
• Familiarity with Git, pytest, dependency management tools such as Poetry or UV, and code quality practices like pre-commit and linting.
• Experience with cloud platforms such as GCP, including tools like Vertex AI and Cloud Storage, or equivalent services.
• Understanding of containerization and orchestration concepts such as Docker and Kubernetes.

Preferred Skills

• Experience using Ray for distributed training or inference.
• Exposure to Hadoop ecosystem tools such as Hive, HDFS, or Spark on YARN.
• Knowledge of ML monitoring, drift detection, and operational support practices.
• Familiarity with infrastructure-as-code tools such as Terraform or Cloud Deployment Manager.
• Background in retail, supply chain, or demand forecasting environments.
• Experience partnering with data science teams to productionize research-driven solutions.
• Comfort working in CI/CD-driven development environments for ML workflows.
• Interest in building reliable, scalable systems that support business-critical forecasting needs.

Horizontal is committed to fostering an inclusive, equitable, and welcoming environment where diverse perspectives are valued and respected. We encourage candidates from all backgrounds to apply and join a team culture grounded in collaboration, integrity, and belonging.

By applying for this position, you acknowledge and agree that Horizontal Talent may contact you regarding your application using automated technology, including phone calls, SMS/text messages, or email, which may be delivered by our virtual AI recruiter, Alex.