Skip to content
View jmsung's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Scale AI
  • San Francisco

Block or report jmsung

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jmsung/README.md

Hi there 👋

I am an AI System Architect and Bio AI Scientist with 15+ years of experience across biophysics, genomics, protein engineering, production ML, and biological data platforms.

I have built next generation sequencing systems SBX at Roche, AI guided protein engineering pipelines at Addition Therapeutics, frontier LLM reasoning evaluation workflows at Scale AI, and hierarchical AI agent systems at Sailplane.

My work focuses on Bio AI for drug discovery, protein design, genomics, precision health, biomedical foundation models, and agentic AI systems.

Outside of work, I am a lifelong swimmer and avid runner.

✍️ I write LatentCell — Bio × AI — a blog on biology, AI, and where they meet: TL;DR for the curious, depth for the specialist.

🔭 Currently working on:

bio-reasoning: Agentic system predicting single-cell perturbation outcomes for the BioReasoning Challenge (MLGenX @ ICLR 2026)
Einstein Arena: JSAgent, ranked #1 overall on open math and science optimization problems
HFC: Evaluating generative AI reasoning models and prompt engineering at Scale AI
• AI agent driven drug discovery for cardiovascular disease and cancer
• AI powered multi agent fact checking system
• Advancing AI innovation in medical centers and hospitals
Precision Health Agents: Multi agent systems for precision health

🧬 Previously worked on:

Hierarchical AI Agents: Structured knowledge systems for hierarchical AI agents in real world production environments
AI Assisted Protein Design: Protein language models and few shot active learning for AI guided genome editing at Addition Therapeutics
AI Security Systems: LLM powered systems for secure real time communication and trusted environments
Digital Pathology: Pancreatic cancer survival prediction from whole slide images
SBX: High throughput nanopore based single molecule sequencing at Roche Sequencing Solutions, including data science and ML contributions to a Guinness World Record human genome sequencing platform

🎓 Research background:

• PhD in Applied Physics from Stanford University
• Postdoctoral research at UCSF and Stanford School of Medicine

📫 Get in touch:

Email
LinkedIn
Blog — LatentCell (Bio × AI)
Google Scholar

Pinned Loading

  1. einstein einstein Public

    Einstein Arena competition solvers

    Python 6

  2. precision-health-agents precision-health-agents Public

    Precision Health Agents

    Python 2