Senior Software Engineer, Generative AI, Gaming at Google · Bengaluru

Design industry-first evaluation suites and reward models (using RLHF and gameplay telemetry) to systematically quantify subjective game quality, balance, and core loop fun, while deploying autonomous multi-agent frameworks to playtest generated code and verify physical logic before release. Address the spatial and interactive blind spots of standard LLMs by fine-tuning models with deep domain knowledge in 3D mathematics, engine architectures and physical reasoning (gravity, momentum, collisions), building frictionless bridges directly into real-time render loops. Drive the foundational research and deployment of rapid-iteration generative models—leveraging distillation algorithms for sub-second, transparent 2D sprite generation and adaptive-resolution Diffusion Transformers (DiTs) to generate complex, fully rigged 3D meshes (using lossless O-Voxel representations). Design intelligent, multi-agent playtesting frameworks where AI agents simulate playthroughs of code and levels to rigorously verify physical logic, boundary constraints, and objective playability before release.