Summary
Tianqi Liu is an ML-focused software engineer with six years of experience building reinforcement learning and LLM systems, currently a Member of Technical Staff at Hark. Previously as a Senior ML Engineer at Roblox, he led internal fine-tuning frameworks and RL environments that enabled Roblox’s first in-house LLMs to outperform proprietary baselines on complex scripting tasks at billion-token scale. His background includes productionizing RL-driven policies at Google and competitive game-AI work at Tencent, reflecting a rare blend of applied RL, systems engineering, and product-focused ML. Based in California with an MS from Brown and a BS from UCLA, he gravitates toward treating real-world problems as RL problems—designing reward structures, evaluation pipelines, and multi-agent training rigs that bridge research and production.
6 years of coding experience
1 year of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Brown University
Bachelor of Science - BS, Math of Computation; Economics, Bachelor of Science - BS, Math of Computation; Economics at University of California, Los Angeles