MZMinghan (Max) Zhu
Minghan Zhu at the San Francisco waterfront with the Bay Bridge in the background.

San Francisco, CA

Minghan (Max) Zhu

Research engineer and Associate Specialist, Department of Neurology, UCSF.

Associated with UCSF Weill Institute for Neurosciences

I build the data infrastructure, neural signal models, and clinician-facing software behind adaptive DBS research at UCSF. My work turns implanted-device recordings, wearable data, sleep measures, and clinical assessments into reproducible ML pipelines for biomarker-guided neuromodulation.

View CVLinkedIn

Publications

Neural decoding posters, conference abstracts, and patent work.

Profile

Research software for neural signals, adaptive DBS, and applied ML.

I am a computer scientist working between machine learning, neural engineering, and clinical research operations. In UCSF Neurology, I help design and maintain a custom adaptive DBS pipeline for Parkinson's disease studies, connecting simulator-driven parameter testing, probabilistic stimulation-effect models, surrogate neural-signal generation, symptom-profile metrics, and constrained optimization for clinician-reviewed parameter selection.

That work sits on longitudinal, multimodal data from implanted sensing devices, wearables, sleep recordings, clinical assessments, and device logs. My day-to-day focus is making experimental ML systems reliable, reproducible, and usable by investigators and clinicians, while keeping enough domain context to reason about neural signals, device constraints, and the clinical questions behind the code.

Before UCSF, I built data-heavy software across healthcare ETL, LLM search, IoT systems, and semantic catalog mapping. That background shaped how I approach research engineering: rigorous enough for science, practical enough for real workflows, and designed so specialists can inspect, trust, and extend the system.

Adaptive DBS ML pipelines for Parkinson's disease and broader adaptive neuromodulation

Multimodal neural, wearable, sleep, clinical, and device-log data infrastructure

Patient-specific signal processing, probabilistic modeling, surrogate data generation, and constrained optimization

Clinician-facing decision-support visualizations and reproducible research software

5integrated modules in a custom aDBS ML pipeline
24patient longitudinal study data design across neural, wearable, sleep, and clinical sources
2neural decoding conference publications
1patent application publication in catalog mapping

Experience

Research engineering across neuroscience, healthcare data, and applied ML systems.

May 2025 - Present

Associate Specialist, Department of Neurology, UCSF

University of California, San Francisco (UCSF) · San Francisco, CA

Building ML and data infrastructure for adaptive DBS research, from neural signal processing to clinician-reviewed parameter-selection workflows.

  • Design and maintain pipelines for implanted neural recordings, wearable motor data, sleep measures, clinical assessments, and device telemetry.
  • Develop ML modules for adaptive DBS research, including stimulation simulation, probabilistic biomarker response modeling, surrogate LFP generation, symptom-profile metrics, and constrained optimization.
  • Build clinician-facing visualization and analysis tools that support review of adaptive stimulation parameters and experimental outcomes.
  • Adaptive DBS
  • Neural devices
  • Signal processing
  • Clinical ML

Sep 2024 - May 2025

Co-Founder & Solutions Architect

ANIUNA Inc. · New York, NY

Co-founded an AI pet-tech startup funded by the Eugene M. Lang Center.

  • Designed and implemented a custom ERP system for pet product manufacturers, integrating with CRM and inventory management systems.
  • Reduced manual data entry time by 67% through workflow automation.
  • Used SDXL, ControlNet, Shap-E, and agentic LLMs to build a semi-supervised prototype pipeline for custom pet apparel design.
  • ERP
  • LLMs
  • SDXL
  • ControlNet
  • Supply chain

Aug 2023 - May 2025

Software Engineer

Cerno Labs · New York, NY

Built LLM-powered search and due-diligence software for vertical research.

  • Designed and built an enterprise-grade LLM search engine with a Next.js frontend and Redis caching for high-speed results.
  • Developed an agent-based copilot for financial due diligence with real-time analysis of filings, reports, and social media.
  • Helped triage leads and generate investment insights through research automation.
  • LLM search
  • Next.js
  • Redis
  • Agents
  • Finance

Apr 2023 - Aug 2023

Software & Data Engineer Intern

Cadence OneFive Inc. · New York, NY

Created housing data pipelines and analytics tooling for carbon analysis.

  • Developed Airflow pipelines for municipal housing data ingestion, expanding coverage and improving accuracy.
  • Built a web portal for US housing carbon analysis with Laravel, PHP, and React.
  • Reduced manual entry time by 37%.
  • Airflow
  • React
  • Laravel
  • Housing data

May 2022 - Aug 2022

Software Engineer Intern

Cedar Cares Inc. · New York, NY

Improved healthcare data ingestion, reconciliation, and support diagnostics.

  • Redesigned Cedar's SFTP data puller with Python, Django, PostgreSQL, and Airflow.
  • Consolidated 43 providers, patched an ETL vulnerability, and built HIPAA-compliant pipelines for real-time patient record reconciliation.
  • Standardized alerting runbooks and reduced support engineering time by deduplicating AWS CloudWatch and Sentry diagnoses.
  • Healthcare data
  • Python
  • Django
  • Airflow
  • PostgreSQL
Read full resume

Research

Current and past research in neural signals, IoT systems, and language/computer vision.

May 2025 - Present

Associate Specialist

University of California, San Francisco (UCSF) · Department of Neurology / UCSF Weill Institute for Neurosciences

Research role focused on adaptive DBS, neural signal analysis, and ML/data infrastructure for movement, motivation, and sleep studies, with clinician-facing visualization tools for aDBS optimization.

Jan 2021 - May 2021

Research Assistant

Columbia University · Prof. Gil Zussman

Used signal analysis and machine learning in the NSF-funded COSMOS smart-city IoT intersections project to optimize traffic flow, reduce congestion, and improve urban safety in New York City.

May 2019 - Dec 2019

Research Assistant

Columbia University · Prof. Henning Schulzrinne

Developed a heuristic system that automatically summarizes local government meeting videos using language processing and computer vision to extract key segments.

Education

Computer science training at Columbia and Brandeis.

Columbia University

New York, NY

  • Master of Science in Computer Science, Sep 2021 - Feb 2023
  • Bachelor of Science in Computer Science, Sep 2018 - May 2020

Brandeis University

Waltham, MA

  • Majored in Computer Science before transferring to Columbia University, Sep 2015 - May 2018

Technical Stack

Comfortable from experimental analysis to deployed research infrastructure.

Languages

  • Python
  • Java
  • C#
  • TypeScript
  • JavaScript
  • SQL
  • Go
  • C++
  • Swift
  • MATLAB
  • R

Frameworks

  • React
  • Next.js
  • Node.js
  • Flask
  • Django
  • Spring Boot
  • .NET Core

ML & Data

  • TensorFlow
  • PyTorch
  • Scikit-learn
  • Pandas
  • NumPy
  • Airflow
  • Redis
  • PostgreSQL
  • MongoDB

Cloud & Infrastructure

  • AWS
  • GCP
  • Azure
  • Docker
  • Kubernetes
  • Terraform
  • Jenkins
  • GitHub CI/CD

Contact

Open to research engineering and scientific ML conversations.

EmailLinkedIn