Brian Young

• Led development of a vision model to identify maximum land area for accessory dwelling unit (ADU) in residential properties from satellite aerial images across the US. •• Sourced aerial imagery data from multiple vendors and perform quality/pricing tradeoff analysis on datasets. •• Hired and trained data annotators, cross validated labeling jobs to ensure quality falls within 90% accuracy. •• Evaluated three image segmentation models on two datasets, and finetuned final model to achieve 90% mIOU and 85% accuracy improvement in predicting max land ADU area, matching human baseline performance. •• Identified bottlenecks in training pipeline including third-party library performance issues and improved training speed by 2.5x on multi-GPU training cluster. • Supervise project on customer credit allocation system to achieve cost optimization and tenant isolation on AI services (ongoing).

• Led Whole Food Market (WFM)/3P integration with Amazon Fresh Store’s (AFS) next generation order fulfillment services to improve associate’s order fulfillment rate by 3% with 10MM annual profit gain in NA, EU and JP. •• Contributed to architectural, testing, release/rollback designs and delivered project at European Union sites over 8 months. •• Supervised 5 away-team devs including design reviews, feature work, bug fixes, and timeline management. •• Collaborated with 5 cross-org teams/stakeholders to design and scope for 8+ initiatives for future milestones. • Implemented next generation fulfillment planning and task prioritization/assignment services for Whole Food Market, Amazon Fresh Store, and Prime Now (UFF) business to support 5M+ shipments/day for future migration. • Led 10+ weekly meetings with accounting stakeholders to align and implement incremental solutions for UFF inventory cost reconciliation issue while supporting service ownership transition within 3 month. • Designed and fixed UUID overflow issue, extending legacy Amazon Fresh Store/Prime Now warehouse management system by 8+ years. •Onboarded 5 new hires including oncall training and project handoffs to support team attrition over 3 month.

• Led development on a document peer review feature as a key component for the release of company’s enterprise medical credentialing product, accelerating 40K+ credential verifications and 10K+ provider onboardings per year. •• Rearchitected feature with Ruby on Rails/React from a delayed project, reducing project timeline from 13 to 4 months. •• Managed team of 3 and standardized Restful API & Redux best practices, led project with 90% test coverage. • Developed a scalable document printing microservice with Node.js and reduced request timeouts across app from 10% to 0% (occurrence rate), improving customer satisfaction.Increased instance throughput by 8x and reduced latency by 3x compared to replaced monolith service.