Staff/Senior Machine Learning Scientist – Forecasting

This is a fully remote position, open to applicants in New York.

📋 Description

• Take ownership of complete machine learning systems, encompassing scoping, feature engineering, model development, backtesting/validation, deployment, monitoring/alerting, retraining cadence, and enhancements in reliability.

• Develop and sustain evaluation infrastructure that is production-safe, which includes automated backtests, error decomposition, uncertainty quantification, data validation, regression gates, and an auditable model/version lineage.

• Create AI-assisted and agentic development workflows, like Claude Code, which incorporate human review and measurable quality gates.

• Establish success metrics aligned with business outcomes and effectively communicate assumptions, limitations, and risks to stakeholders.

• Produce high-quality, testable code and support reproducible workflows.

• Collaborate across functions to convert business requirements into a prioritized technical roadmap and measurable impact.

• Develop and refine forecasts across various time horizons and business segments, encompassing demand, inventory, supply chain, and resource allocation.

• Transform forecast outputs into products with clear definitions, assumptions, versioned releases, and reports on changes and uncertainty.

• Utilize feature engineering, uncertainty quantification and calibration, and hierarchical/segmented forecasting when applicable.

• Work in partnership with leaders in operations, supply chain, inventory, finance, and marketing.

⛳️ Requirements

• Senior level: Over 5 years of experience in applied ML/data science, including ownership of models in production.

• Strong expertise in forecasting utilizing time-series methods, feature engineering, and thorough backtesting, or in-depth knowledge of Bayesian statistical methods and probabilistic programming.

• Solid foundation in statistics and comfort with probabilistic forecasting and the articulation of uncertainty.

• Proficient in Python or R and SQL; capable of writing production-quality, testable code.

• Exceptional communication skills and ability to collaborate effectively with non-technical stakeholders.

• Experience in responsibly utilizing AI-assisted development workflows, including verification loops, reproducibility, and automated checks.

• Staff level: More than 8 years in applied ML/data science, or a PhD with over 3 years of applied experience.

• Proven experience at the staff level in building comprehensive ML systems, encompassing backtesting frameworks, scheduled retraining, monitoring/alerting, and automated reporting.

• Capability to navigate complex systems and make sound architectural decisions with a high degree of autonomy.

• Experience in technical leadership and mentoring.

• Candidates proceeding to the first interview must present a photo ID on camera.

• Submission of a resume and cover letter is required.

🏝️ Benefits

• Annual profit award or bonus, contingent upon company performance.

• Eligibility for remote work within the U.S.

• Final interviews conducted in person at a Penguin Random House location.