Young Chin | Bob | 秦洋

SZ, China

Currently seeking opportunities in multimodal and omni models, AI agents, and AIGC.

Previously spent one year as a Senior Engineer at Quwan Technology in Guangzhou, focusing on multimodal understanding and AI agent systems.

Started my career at MagicLight, working on AIGC for long-form story video generation.

Yang Chin

Expertise

Multimodality

  • Vision-Language and Omni Models
  • VLM-based OCR
  • Multimodal Speaker Diarization
  • Long Video Understanding

AIGC

  • ID Preserving & Face Swap
  • Regional Controlled Generation
  • Subject-Consistent Video Generation

AI Agents

  • Agent Frameworks
  • Memory Systems
  • Personality and User Modeling

AI Security

  • Multimedia Forensics
  • Deepfake Detection

News

Jun 2026 Open-sourced Know Each Other, a Claude skill that builds persistent psychological profiles so AI can truly know you across sessions.
May 2026 Open-sourced DeepTalk Agent, a fully local voice AI assistant running on macOS Apple Silicon with MLX.
Sep 2025 Joining AllVoiceLab at Quwan Technology , All Voice Lab Team.
Sep 2024 Invited interview as Outstanding Postgraduate Students in MUST. Watch video.
Jun 2024 Joining MagicLight to build AIGC platform. Try 白日梦AI.
Nov 2023 MAPS won Bronze Award and Best Application Award at GBA IT Application Competition.
Jun 2023 Project MAPS won Winner Award (Top 3) at GBA IT Application Development Competition Macau Sub-Competition.

Blog

Agent

Smart Marketing Agent

Read article
OCR

Video Subtitle OCR

Read article
Memory

Know Each Other

Read article
Agent

DeepTalk Agent

Read article
AIGC

AIGC Weekly 05/24

Read article
AIGC

AIGC Weekly 05/17

Read article

View all posts →

Yang Chin

AI Engineer · Shenzhen, China

Education

  • M.S. in Applied Mathematics and Data Science, Macau University of Science and Technology, 2024
  • B.E. in Data Science and Big Data Technology, Foshan University, 2022

Experience

Senior Engineer · AllVoiceLab, Quwan Technology · Sep 2025 – Aug 2026

  • Developed multimodal solutions for video translation across text, speech, and vision.
  • Designed AI agent systems, including agent workflows and memory systems.

AI Engineer · MagicLight · Jun 2024 – Aug 2025

  • Built an AIGC platform for long-form story video generation across text, image, and video.
  • Worked on identity-preserving and regional-controlled image generation, as well as pose-controlled generation.
  • Developed prompt-engineering workflows for scripts and image-to-video models.

AI Intern · AFS Ltd., Digital AI Group · Feb 2024 – May 2024

  • Worked on human portrait generation and pose-driven video generation.

Research Intern · Zhuhai UM Research Institute · 2022 – 2023

  • Researched synthetic image detection, advanced AIGC technology, and AI security.