Data Scientist II

About the role

Toast is driven by building the restaurant platform that helps restaurants adapt, take control, and get back to what they do best: building the businesses they love. The role involves embedding data science capabilities directly into the Toast platform through close collaboration with engineers and product managers to develop statistical and machine learning models that power key product lines. You will apply a diverse set of expertise including data mining, statistical analysis, and machine learning to deliver impactful, objective, and actionable data insights. These insights will enable informed business and product decisions that drive growth and engagement across the restaurant ecosystem. You will partner with line of business teams and collaborate with product managers, engineers and other data scientists to foster data-driven decisions that yield significant impacts. The position requires the ability to effectively communicate analysis, insights and recommendations to high-level business partners in verbal, visual and written formats. You will thrive in a dynamic and rapidly evolving environment where agility and adaptability are essential.

Key facts

What you'll do

• Identify and define complex business problems and translate them into data science solutions that generate measurable value for restaurant partners.
• Design and develop advanced statistical and machine learning models that are integrated into production systems powering core Toast product lines.
• Partner with cross-functional teams including sales, marketing, and product to discover business opportunities and formulate data-driven strategies.
• Conduct rigorous offline and online evaluations of model performance to ensure robustness, accuracy, and reliability in production environments.
• Implement machine learning techniques spanning supervised learning, unsupervised learning, graph algorithms, deep learning for NLP, recommendation systems, and generative AI.
• Leverage Python and SQL extensively while utilizing modern ML frameworks such as scikit-learn, Tensorflow, and PyTorch for model development.
• Build and maintain model workflow orchestration pipelines using tools such as Airflow to automate data processing and training cycles.
• Collaborate closely with engineers to deploy models into scalable cloud architectures with a strong emphasis on AWS services including SageMaker, DynamoDB, Athena, and Glue.
• Communicate sophisticated quantitative analysis clearly and precisely to non-technical stakeholders through visualizations, reports, and presentations.
• Contribute to experimentation frameworks by supporting A/B testing and other methodologies that measure product impact and guide decision making.
• Mentor junior analysts and data scientists by sharing best practices in software engineering, testing, and version control.
• Maintain and improve data pipelines to ensure high quality, timely, and reliable datasets for analysis and modeling.
• Explore emerging techniques in large language models and retrieval-augmented generation to enhance platform capabilities.
• Drive end-to-end ownership of data science projects from initial hypothesis through deployment and post-launch monitoring.

Requirements

• Hold a Bachelors degree in computer science, engineering, math, statistics, economics, or other quantitative discipline; a Masters degree is preferred.
• Bring 2+ years of data science experience in an industry environment working with real-world datasets and stakeholders.
• Demonstrate solid foundations in statistical analysis and machine learning concepts including regression, classification, clustering, and model evaluation.
• Show experience with advanced machine learning techniques such as supervised and unsupervised learning, graph algorithms, deep learning including NLP, recommendation systems, and generative AI.
• Exhibit proficiency in Python and SQL with hands-on experience using ML frameworks like scikit-learn, Tensorflow, and PyTorch.
• Have practical experience with cloud solutions, preferably within AWS tooling such as SageMaker, DynamoDB, Athena, and Glue.
• Possess experience using model workflow orchestration tools like Airflow to manage complex data science pipelines.
• Display a proven ability to collaborate effectively with engineers, product managers, and other cross-functional teams.
• Communicate excellent verbal and written skills with the capacity to distill complex quantitative analysis into clear, precise, and actionable narratives.
• Apply structured problem-solving skills to navigate ambiguity and drive projects forward in a fast-paced setting.
• Demonstrate ownership and accountability for delivering high-quality results on schedule while balancing multiple priorities.
• Show commitment to continuous learning and adapting to new technologies, methodologies, and best practices in the data science field.

Nice to have

• Experience working on LLM applications, including prompting, RAG, and evaluation methods.
• Familiarity with software engineering best practices and tools including object-oriented programming, test-driven development, CI/CD, git, and shell scripting.
• Experience shipping machine learning systems in production environments at scale.
• Background in A/B testing and other experimentation methodologies for effective product launch measurement and optimization.

Practical notes

This role is based in Canada and the specific engagement type is detailed in the source information. Candidates must be eligible to work in Canada without sponsorship requirements. No compensation details are provided in the source material. The position involves dynamic collaboration across engineering, product, sales, and marketing teams in a fast-evolving technology environment.