# Tianyu Liu > CUDA developer. Senior software engineer. Location: United States, United States Profile: https://flows.cv/tianyuliu Software engineer, with expertise in GPU computing and Monte Carlo simulation of radiation transport. Hobbyist video game developer. ## Work Experience ### Senior Software Engineer @ NVIDIA Jan 2024 – Present Maintainer of KvikIO, an open-source, high-performance I/O library powering the RAPIDS/cuDF ecosystem. Design and optimize Linux I/O paths. for GPU data ingestion at scale ### Senior Software Engineer @ DoorDash Jan 2024 – Jan 2024 | United States • Worked on DoorDash Dot at Doordash Labs. Developed a lightweight API to trace GPU activities. Implemented a feature to analyze GPU memory pool fragmentation. ### Senior Software Engineer @ Motional Jan 2023 – Jan 2024 | Boston, Massachusetts, United States • On the robotics infrastructure team, developed a GPU utility library to facilitate CUDA development. • For the autonomy AI tasks, developed and optimized CUDA kernels, and performed runtime GPU optimizations. ### Software Development Consultant @ IQ Medical Imaging Jan 2022 – Jan 2022 | Belmont, Massachusetts, United States • Verified segmentation algorithms for the Advance Tumor Imaging Quantification software for FDA review. • Developed virtual phantom generation workflow. ### Researcher @ Massachusetts General Hospital Jan 2019 – Jan 2022 | Boston, Massachusetts, United States • Developed a HIP-based library to accurately calculate effective atomic numbers in dual energy CT imaging for colon polyp detection on Nvidia/AMD GPUs. • Developed an Unreal Engine-based software ElbowCare to optimize baseball athletes’ elbow surgery procedure. • Maintained a research software 3DQI designed for quantitative medical image analysis. Developed a Python/R-based pipeline to enable routine radiomics analysis and machine learning on medical images for tumor detection and diagnosis. ### Computer Scientist @ Rensselaer Polytechnic Institute Jan 2014 – Jan 2019 | Troy, New York, United States • Developed GPU and Intel Many Integrated Core (MIC, aka Xeon Phi)-accelerated Monte Carlo code ARCHER to simulate radiation transport of photons for CT imaging dosimetry. • Developed GPU-accelerated photon-electron coupled transport code for radiotherapy dose planning (including HIP port and testing on an AMD GPU). Explored proton transport and magnetic field-influenced electron transport. • Investigated the vectorization feasibility for one-group neutron transport on GPUs. • Maximized the performance of photon transport and one-group neutron transport codes using a hybrid CPU-GPU-MIC system. • Optimized the proxy application XSBench on CPU and accelerators, respectively. • Optimized the performance and accuracy of atomic-add operations in GPU-accelerated Monte Carlo simulation. • As guest speaker, gave lectures on Monte Carlo method and radiation dosimetry. ### Research intern @ Massachusetts General Hospital Jan 2013 – Jan 2013 | Boston, Massachusetts, United States • Performed dual-energy CT scanner modelling and validation • Performed Monte Carlo dose calculation ## Education ### Doctor of Philosophy - PhD in Nuclear Engineering and Science Rensselaer Polytechnic Institute ### Bachelor's degree in Engineering Physics Tsinghua University ## Contact & Social - LinkedIn: https://linkedin.com/in/tianyu-liu-857b794b - Portfolio: http://tianyuliukingcrimson.wordpress.com/ - Portfolio: https://scholar.google.com/citations?user=63s6dqQAAAAJ&hl=en - GitHub: https://github.com/kingcrimsontianyu --- Source: https://flows.cv/tianyuliu JSON Resume: https://flows.cv/tianyuliu/resume.json Last updated: 2026-03-31