Feiya SHU — AI Product Manager

I research, build and ship human–AI systems.

From research and product judgment to working systems.

Selected work

Projects

AI-native career workspace

Vocatrya

From interview-feedback research to a working AI-native career workspace.

From information to decision, from decision to action. It connects scattered career experience, job opportunities, resume materials, and the application process in one place — and an executable AI agent helps turn natural-language requests into real in-product actions.

Independent Product Lead & Developer · Structured workspace + actionable AI agent

View case study

Agent runtime composition system

CraftStation

Native power by default. Model × Harness customization by choice.

One desktop workspace for models, harnesses, accounts, MCP servers, and Skills. Auto follows each model's native runtime; a saved Recipe puts a chosen Model × Harness combination to work.

Product Designer & Tester · Windows x64

View case study

Research

  1. Dynamic Representation Augmentation for Multimodal Emotion Recognition with MLLMs

    How multimodal emotion recognition can keep short-term visual and acoustic dynamics explicit, instead of leaving a language model to reconstruct them.

About Me

I work across product discovery, AI system design and implementation.

  • Product discovery & problem framing

    Turn user behavior, research evidence and product constraints into clear product decisions.

  • AI product definition & evaluation

    Define AI workflows, feedback loops, guardrails and evaluation criteria for human–AI systems.

  • Cross-functional prototyping & shipping

    Work closely with design and engineering, prototype when needed, and stay involved through implementation.

Currently
MPhil researcher · HKUST(GZ)
Focus
AI products · Human–AI interaction
Based in
Guangzhou & Shenzhen, China