Staff Data Scientist

About the role

Toast creates technology to help restaurants and local businesses succeed in a digital world, helping business owners operate, increase sales, engage customers, and keep employees happy. As a Staff Data Scientist, you will own the full machine learning lifecycle for high-impact initiatives such as menu recommendation, demand forecasting, offer targeting, and guest personalization. You will serve as a technical thought partner across product and engineering teams, set best practices, and influence the roadmap for ML-driven products that support key business outcomes. Your work will directly shape strategic decisions and enhance customer experience at scale while fostering a culture of innovation. This role represents a current vacancy within our growing data science organization.

Key facts

What you'll do

• Own the end-to-end design, development, and monitoring of scalable ML systems for mission-critical use cases including menu optimization, demand forecasting, offer targeting, and guest personalization.
• Design and implement advanced statistical and machine learning models that improve product performance, operational efficiency, and customer insights across digital touchpoints.
• Collaborate closely with engineers, product managers, and business stakeholders to define project scope, success metrics, and integration strategies for data-driven features.
• Guide architectural decisions, establish modeling standards, and champion best practices for experimentation, validation, and productionization of ML solutions.
• Mentor fellow data scientists, elevate technical design reviews, and provide actionable feedback to raise the overall technical bar within the team.
• Proactively identify opportunities where data science can generate business value and lead cross-functional efforts to deliver measurable impact.
• Leverage cutting-edge AI tools to enhance personal development velocity, streamline workflows, and contribute to a culture of innovation and continuous improvement.
• Partner with analytics and operations teams to translate ambiguous business questions into well-scoped analytical and ML solutions that drive decisions.
• Ensure models are robust, interpretable, and compliant with relevant data governance and privacy standards where applicable.
• Contribute to the broader data platform strategy by engaging in discussions around data quality, feature stores, and model deployment pipelines.
• Evaluate emerging research and translate novel techniques into practical applications that address real-world business constraints.
• Communicate complex analytical findings and model outcomes to both technical and non-technical audiences through clear documentation and presentations.

Requirements

• Bring 5 or more years of hands-on experience in data science with a proven track record of delivering production ML systems that drive measurable business outcomes.
• Demonstrate deep knowledge of statistical modeling, machine learning methods including tree-based models, time series, and deep learning, and model evaluation frameworks.
• Show experience working with real-world product data at scale and successfully translating ambiguous problems into well-defined ML solution designs.
• Have hands-on background with distributed data processing and training, real-time inference systems, and ML Ops frameworks to deploy reliable models.
• Have prior experience mentoring other data scientists or acting as a technical lead in cross-functional settings.
• Show demonstrated experience leading experimentation such as A/B testing, applying causal inference methods, and building real-time decision systems.
• Write proficient Python and SQL, and have practical experience with ML frameworks such as scikit-learn, PyTorch, and TensorFlow.
• Uphold strong software engineering principles including modular design, disciplined version control, comprehensive testing, and robust CI/CD practices.
• Have hands-on experience with cloud platforms, especially AWS, and familiarity with tools such as SageMaker, Athena, Glue, DynamoDB, and Bedrock.
• Communicate effectively with both technical and non-technical stakeholders, influencing decisions through logic and clarity of narrative.
• Show strong business acumen and the ability to align technical solutions with overarching company goals and priorities.
• Commit to working within the local legal and regulatory framework applicable to data usage and model deployment in Canada.

Nice to have

• Hold an advanced degree in Computer Science, Statistics, or a related STEM field.
• Have experience with MLOps tooling for monitoring, drift detection, retraining, and model explainability.
• Have experience fine-tuning large language models and applying reinforcement learning from human feedback (RLHF) to improve model performance and alignment.

Practical notes

This role is based in Canada and is a current vacancy. No additional details regarding hours, travel, visa requirements, or specific deadlines were provided in the source material.