Photo of Chris KAMBIMBI

About Me

Hello! I'm Chris (Chrispine KAMBIMBI | 卡穆 Kamu) 👋 A curious AI Safety Researcher & Software Engineer passionate about ensuring AI systems are robust, ethical, and trustworthy — especially in high-stakes domains like healthcare.

My work revolves around adversarial robustness in medical AI, where I investigate vulnerabilities in multimodal models (think: combining text, images, and patient data) to hopefully prevent catastrophic failures. Currently, I'm pursuing my M.S. in AI & Software Engineering at Fudan University.

Interests

  • AI Safety
  • Medical AI
  • GenAI

Languages

  • English★★★★★
  • Chinese★★★★☆

Resume

Education

  • Postgraduate Degree in Software Engineering (Professional degree)

    Fudan University, Shanghai

    Sep 2023 – Present

    • Focus: Trustworthy AI, large language models, and multimodal systems.
    • Relevant Coursework: Machine Learning, Deep Learning, Trustworthy Machine Learning, Big Data Analytics, Software Management.
    • Research: Enhancing robustness of multimodal LLMs against adversarial attacks in medical applications, improving safety.
  • Bachelor's Degree in Electronic Information Engineering

    Tongji University, Shanghai

    Sep 2019 – Jun 2023

    Relevant Coursework: Artificial Intelligence, Signal Processing, Embedded Systems.

  • Chinese Language Certificate (HSK 4)

    Tongji University, Shanghai

    Sep 2018 – Jun 2019

    Completed my Chinese language studies and obtained HSK 4 certificate.

Professional Experience

  • GenAI Development Support (Operations)

    Dazzle AI, Shanghai

    Mar 2023 – Oct 2023

    • Collaborated with engineers to develop a text-to-image generation tool, optimizing prompts and datasets to improve output quality by more than 15%.
    • Conducted model testing, identifying reasoning errors in generative outputs and enhancing data pipelines.
    • Authored technical documentation to improve user adoption and model usability.
  • AI Content Moderator

    CivitAI, Remote

    Apr 2023 – Dec 2023

    • Analyzed generative AI outputs to ensure alignment with safety and ethical standards, contributing to model refinement.
    • Provided feedback to developers on content quality, improving LLM performance for community applications.
    • Contributed to maintaining a safe and compliant online environment focused on AI models and resources.
  • Community Operations Intern

    ET & Larix, Shanghai

    Jun 2022 – Dec 2022

    • Supported data-driven community engagement by analyzing user trends, leading to a 10% increase in platform activity.
    • Moderated AI-generated content, ensuring compliance with safety protocols and enhancing user trust.

Projects

  • Adversarial Robustness in Multimodal LLMs (Medical Domain)

    Fudan University

    Ongoing

    • Investigating adversarial vulnerabilities in multimodal LLMs to improve reasoning accuracy and safety for medical diagnostics.
    • Developing techniques to mitigate attacks.
    • Tech Stack: Python, PyTorch, Hugging Face Transformers.
  • Bluesky Web Client

    Personal Project

    2025

    • Built a web client for Bluesky using AT Protocol, enabling decentralized social networking with real-time user interaction.
    • Implemented responsive UI with Vue.js and optimized API calls for performance.
    • GitHub: imaiimaiimaiimaiimaiimai/bluesky-client

Skills

  • Programming

    Python, JavaScript

  • AI/ML

    Large Language Models, NLP, Prompt Engineering, PyTorch, Hugging Face

  • Web Development

    React.js, Next.js, Node.js, Vue

  • Tools

    AWS, Google Cloud, Jupyter Notebooks, Docker

  • Languages

    English, Chinese

  • Soft Skills

    Problem Solving, Team Collaboration, Technical Writing

Hobbies & Interests

  • Photography

    Minimalist approach to photography, focusing on capturing authentic moments with natural light and minimal post-processing. Started in 2025 as a creative counterbalance to technical work.

  • AI Research

    Generative AI, AI Safety, NLP, Medical AI