Sanjay Roberts Email & Phone Number

San Francisco, California, US

• Managed Data Platform’s aggregation and ETL framework, responsible for 10+ PB of data
• Led the SQL validation guardrails project to optimize customer queries. Developed backend APIs, UI workflows, and customer documentation, laying the groundwork for scalable data quality improvements.
• Managed the GDPR-compliance migration, resulting in $4M savings and a 30% reduction in underutilized datasets. Coordinated with eng and product teams, developing automated processes to keep projects on schedule.
• Built and migrated Twitch’s event data to a new schema registry platform, successfully transitioning 50 teams. Enhanced data governance and quality, created self-service documentation, automated imports, and led the.
• Onboarded and mentored 10 engineers. Led technical interviews and influenced hiring decisions. Delivered presentations to promote data eng best practices at the org-level and Engineering Summit.
• Participated in on-call rotation, trouble-shooting customer issues, creating tools for DQ analysis, and improving customer query times

Menlo Park, CA, US

• Led the Purchase Experience and Shopify Checkout API migration for Facebook and Instagram Shops.
• Collaborated with cross-functional teams to implement e-commerce metrics for experimentation and tracking.
• Built pipelines and dashboards for key metrics (GMV, transactions, conversion rate, error rate, cancellation rate).
• Improved on-call rotation and pipeline SLAs by resolving upstream bottlenecks, enhancing system reliability.

Stamford, Connecticut, US

• Built and managed production pipelines for forecasting, dynamic scheduling, and customer churn models.
• Designed scalable architecture and implemented serverless frameworks, enhancing performance and campaign insights.
• Migrated data pipelines from Teradata to Snowflake, ensuring data quality and integrity.
• Deployed forecasting ML models, monitored metrics for accuracy, and developed anomaly detection pipelines.
• Communicated project needs and findings, presenting insights in Tableau and JupyterHub.

Denver, Colorado, US

• Wrangled data, performed EDA, trained and tested language model for custom NLP search engine in Python.
• Integrated Solr search API into product
• Set up and managed Azure VMs and cloud services for product

New York, NY, US

• Translated client requirements into standardized model. Managed 6 product data lifecycles using ETL and data warehouse software to build a central data source for clients
• Performed product generation and integration with the frontend for full deployments with client site
• Mentored client staff in design, management, and modeling of products
• Created timelines, estimates of effort, and product testing requirements

Golden, CO, US

• Built performance-loss model for solar modules in Mathematica
• Performed laboratory experiments on module degradation

Colorado Springs, Colorado, US

• Co-founded this non-profit whose dual mission is to sustainably reduce food waste and improve health equity for low-income populations by providing fresh, nutritious food free of charge
• Saved 300,000 pounds of food
• Raised $125,000 in funding
• Built a volunteer base of 100+ students and community members
• Built relationships with nation-wide grocery store chains and paired chains with food banks
• Managed two full-time employees, the organization is still in operation with 5+ employees

Washington, DC, US

• Built trails in state parks across Texas, Arizona, and Colorado

Master Of Science - Ms, Data Science

Bachelor’S Degree, Mathematics