CV

• Led a research agenda on how LLMs can automate developer workflows in open-source codebases. Scoped the problem space, designed experiments, and developed a prompting framework for automated test generation across AOSP and ChromeOS
• Designed language-agnostic code-graph representations using Kythe to construct structured C++/Java training datasets from large-scale open-source codebases
• Collaborated with DeepMind and CoreML teams to define data specifications and quality criteria for training Google's internal models on open-source code
• Developed an unsupervised root-cause diagnosis method for Android using density-based clustering on T5X embeddings to group infrastructure errors by underlying cause

• Designed API correctness verification for Android Mainline. Defined coverage criteria and developed infrastructure that enabled continuous releases across 800+ million devices and 5 platforms

• Investigated and optimized Android smart-sync performance. Identified bottlenecks and reduced project sync times by up to 99%
• Developed a photomosaic generation algorithm that reconstructs source images by matching and tiling thousands of database images

• Designed a novel interpretable model for multi-agent reinforcement learning in general game playing
• Applied Monte Carlo methods and Nash Equilibria to achieve real-time inference without pre-training

• Developed integer linear programming models that generate digital artwork from mathematical constraints. Every pixel in the output is determined by an optimization solver

• Designed proposals for piezoelectric energy harvesting systems on campus, evaluating feasibility and expected output across candidate sites

• Major GPA: 3.86
• Graduated with High Honors

• Mentored 12+ early-career engineers through Google's Engineering Residency and Early Career Immersion programs
• Guided project scoping, design decisions, and code reviews to accelerate onboarding and independent contribution

• Guided introductory CS students through lab exercises and debugging, reinforcing core programming concepts
• Graded labs and provided detailed feedback to support student learning

• Gained hands-on medical experience in organ donation compatibility testing, processing 50+ protein samples daily

• Assisted filmmakers in interviewing participants and documenting the Smithsonian Peruvian Folk-Like Festival through film and photography