Jiayi Nie smiling on a bridge over the River Cam, with a Cambridge college behind

Jiayi Nie 聂佳艺

PhD student, Computer Science
University of Cambridge

About

I am a PhD student in the Department of Computer Science and Technology at the University of Cambridge, supervised by Dr. Rika Antonova and Prof. Robert Mullins, and part of CamRAL. I previously worked with Dr. Edward Johns in the Robot Learning Lab at Imperial College London.

My PhD is funded by AIxSIM, an ARIA-funded cross-stack simulation effort for novel AI hardware, where I also work closely with Dr. Aaron Zhao, Prof. Timothy M. Jones and Dr. Jianyi Cheng. I build hardware for agents, and agents for hardware.

I want to see a compute stack that rebuilds itself, where agents become the new paradigm of design space exploration, redesigning the very models, kernels, compilers and instruction sets they run on, with every step checked by proof rather than trust.

Research, up the stack

  1. Self-improving agents

    Agents that evolve alongside their own evaluators: Red Queen Gödel Machine

  2. Serving

    Splitting inference stages across specialised hardware: When Does Disaggregation Pay?

  3. Kernels

    Close-to-metal kernel generation for emerging hardware, kernel optimisation for GPUs, and formal verification of kernels: KernelCraft, AReaL-TIK, LARK

  4. Accelerators

    NPU quantisation and design space exploration for agentic inference:PLENA, MemExplorer, diffusion language models

  5. Microarchitecture

    Design space exploration for branch predictors: PIP

Education

Industry

  • 2026Cambridge, UK

    Microsoft Research

    Research Intern, agentic GPU kernel optimisation, with Dr. Jin Xu

  • 2023 – 2025Cambridge, UK

    Amazon

    Software Development Engineer, AWS S3

    Software Development Engineer Intern, Alexa Information

  • 2022 – 2023Cambridge, UK

    Arm

    Part-Time Undergraduate

    Hardware Engineer Intern, Central Technology CPU

Teaching

  • 2025

    Teaching Assistant, University of Cambridge

    Reinforcement Learning

  • 2022 – 2023

    PASS2 Leader, University of Manchester

    Led Peer Assisted Study Sessions, mentoring second-year Computer Science students through the university's student-run peer support scheme. Recognised with a Community Award

Publications * Equal contribution

Talks

Service

© 2026 Jiayi Nie