Yuntao Zhang

Welcome! I am a Senior Scientist at Bristol Myers Squibb based in the San Francisco Bay Area, specializing in high-resolution mass spectrometry and laboratory automation, while developing modern computational tools and agentic solutions. My work bridges experimental bioanalytical chemistry with AI systems—leveraging structural mass spectrometry and intelligent pipelines to accelerate biologics discovery and elucidate complex biomolecular mechanisms.

About Me

• Current Role: Senior Scientist at Bristol Myers Squibb (BMS)
• Expertise:
  • Biologics Mass Spectrometry: Characterizing biologics with peptide mapping, carbene footprinting (epitope/paratope mapping), and bottom-up proteomics.
  • Computational & AI: Applying molecular modeling, deep learning, and AI agents to solve complex scientific problems.
  • Workflow Automation: Developing automated systems to enhance research efficiency and reproducibility.
• Education:
  • Ph.D. in Bioanalytical and Physical Chemistry, University of the Pacific
  • M.S. in Environmental Engineering, University of the Pacific
  • B.S. in Ecology, University of Science and Technology Beijing

Featured Interactive Project

MoE 3D Architecture Visualizer

Three.js / WebGL React 18 Sparse MoE 535B LatentMoE Compression Dynamic Sampling

An open-source interactive 3D WebGL educational visualizer demonstrating modern 500B+ MoE architectural concepts including LatentMoE compression, Quantile-Balanced routing, and real-time dynamic sampling directly in the browser without server dependencies.

🚀 Live Demo 💻 GitHub 📝 Technical Blog 🔍 Details

Interdisciplinary Focus

With a strong foundation in analytical chemistry and an active focus on computational methods, I combine hands-on expertise in mass spectrometry and biologics characterization with modern data science toolchains. I have experience applying and fine-tuning machine learning models—such as exploring ST-Tahoe for single-cell perturbation analysis and Boltz-2 for structural biology—while maintaining reproducible computational workflows across cloud and enterprise platforms (GCP, Domino Data Lab) using Docker and uv. This background enables me to bridge high-resolution experimental measurements with computational analysis to extract deeper biological insights.

Complementing my scientific work, I maintain an active interest in software engineering and algorithms, practicing core data structures and algorithms across Python, C++, and Go to keep core software engineering fundamentals sharp.

Agentic Workflow

Leveraging autonomous CLI agent workflows (Claude Code, Gemini CLI, GitHub Copilot) for rapid full-stack prototyping, scientific pipeline automation, and reproducible research.

Impact & Achievements

• Open-Source AI Architecture Visualization: Developed MoE 3D Architecture Visualizer, an open-source interactive 3D WebGL educational visualizer demonstrating modern 500B+ MoE architectural concepts including LatentMoE compression and expert routing dynamics directly in the browser (Demo / Code).
• Machine Learning & Model Fine-Tuning: Applied and fine-tuned machine learning models, including adapting the ST-Tahoe foundation model for perturbation analysis, analyzing training dynamics, representation spaces, and loss behaviors on enterprise compute platforms.
• Biologics Characterization: Led the implementation of carbene footprinting for high-resolution epitope/paratope mapping, and developed robust LC-MS methods to support bispecific, ADC, and cell therapy programs.
• Mentorship & Leadership: Mentored interns in machine learning pipelines and mass spectrometry workflows. Recognized with the CABS 2026 Mentor Impact Award for contributions to the CABS Data Science Summer Internship Program.

Publications & Research

I have authored multiple peer-reviewed publications advancing the fields of mass spectrometry, peptide/peptoid characterization, and molecular modeling. Rooted in physical chemistry, my research combines gas-phase ion chemistry, high-resolution mass spectrometry, and quantum chemical modeling to elucidate biomolecular structure, chirality, and reactivity. See my publications for details.

Professional Development

I am committed to continuous learning across machine learning, computational biology, and modern software development practices. Selected coursework and certifications include:

• Machine Learning (Stanford/Coursera)
• Deep Learning Specialization (DeepLearning.AI)
• AI Agents (Hugging Face)

Explore all certificates and projects.

Vision

I believe the integration of high-resolution bioanalytical mass spectrometry and modern computational methods holds tremendous potential for biotherapeutics. By pairing rigorous experimental measurements—such as covalent carbene footprinting—with machine learning models and structural biology tools, my vision is to accelerate the development of targeted therapeutics, enhance analytical automation, and help uncover molecular mechanisms underlying human aging and complex diseases.

Feel free to explore my CV, publications, projects, and certificates to learn more about my work. I am always open to new collaborations and opportunities to make a positive impact in the scientific community.