Computer Science + Biomedical Sciences

MUNISH PERSAUD

Building safer AI systems at the intersection of machine learning and healthcare

I believe that as AI systems become more powerful, ensuring their safety and alignment with human values becomes paramount. My work focuses on developing rigorous testing methodologies for bio-foundational AI while creating healthcare applications that genuinely empower patients and practitioners.
University of Central Florida B.S. Computer Science & Biomedical Sciences | Minor in Non-Profit Management

FOCUS AREAS

Specialized expertise across AI safety, computer vision, and biomedical applications

01

AI Safety

Developing adversarial testing frameworks and red-teaming methodologies for generative bio-foundational models. Specializing in vulnerability assessment, jailbreak detection, and safety protocol evaluation.

02

Computer Vision

Implementing pose estimation pipelines, gait analysis algorithms, and real-time inference systems optimized for edge deployment on resource-constrained hardware.

03

Healthcare AI

Architecting HIPAA-compliant ML systems with on-device inference, federated learning considerations, and clinical workflow integration for diagnostic and therapeutic applications.

04

Full Stack Development

Building scalable microservice architectures with React/React Native frontends, Node.js backends, and cloud infrastructure leveraging containerization and CI/CD pipelines.

FEATURED PROJECTS

Healthcare-focused AI systems designed for real-world impact

Senior Design Project with UCF College of Medicine

AI-PEER

Project Manager / AI Engineer / Backend Developer

Mobile application implementing a hybrid CV-NLP pipeline for geriatric fall risk assessment using the PEER clinical framework. The computer vision module performs real-time pose estimation and gait analysis to quantify fall risk scores and validate exercise form compliance. A distilled language model runs inference on-device to deliver context-aware psychological reinforcement. Both models are quantized and optimized for mobile NPUs to ensure patient data never leaves the device. Backend services deployed on Google Cloud with HIPAA BAA compliance. Frontend built in React Native with WCAG 2.1 AA accessibility standards for geriatric usability.

Pose Estimation Model Quantization React Native GCP HIPAA
Medical Administrative Intelligence Agent

MAIA

Co-Founder / Full Stack Developer / AI Engineer

AI-powered platform automating administrative workflows for private medical practices. Validated product-market fit through 50+ physician interviews across multiple specialties. Currently in active development.

Agentic AI Healthcare B2B SaaS
maiamed.ai
Lossless Image Slide Archival

LISA

Founder / Full Stack Developer / AI Engineer

Neural compression system for whole slide images (WSIs) addressing the storage bottleneck in digital pathology where single slides exceed 1GB. Implemented a VQ-VAE architecture with a learned discrete codebook for latent space quantization, paired with a separate decoder network to preserve diagnostic-quality reconstruction. Achieved 84x compression ratio (272.52MB → 3.24MB) with minimal perceptual loss. Built in 36 hours at Startup Weekend Orlando. React frontend communicates with a Flask API backend running inference on a vast.ai L40S GPU instance.

VQ-VAE Neural Compression Flask CUDA Digital Pathology
https://youtu.be/i3qQa6fLZYI
Plastic Surgery Facial Augmentation Tool

AURA

Founder / Full Stack Developer / AI Engineer

Multi-platform surgical outcome prediction system. iOS client built in Swift captures facial geometry and transmits to GPU inference server. Core generation model is DreamOmni2 fine-tuned with LoRA adapters on procedure-specific datasets to predict post-operative facial morphology. React webapp integrates Web Speech API for voice-controlled surgeon interaction. Implemented content filtering guardrails using CLIP embeddings to restrict input/output to facial imagery only.

LoRA Fine-tuning Swift CLIP DreamOmni2 Web Speech API
Campus Event Discovery Platform

FOMO NOMO

Frontend Mobile Developer

Cross-platform mobile application aggregating student organization events into a unified feed. Translated high-fidelity Figma prototypes into production Flutter code with custom widget composition. Implemented infinite scroll pagination with lazy loading for optimized memory footprint. Achieved WCAG compliance through Lighthouse audits, semantic markup, and VoiceOver/TalkBack screen reader testing. Maintained platform parity across iOS and Android rendering pipelines.

Flutter Dart Infinite Scroll Accessibility Cross-Platform

RESEARCH EXPERIENCE

Academic positions driving innovation in AI safety and computer vision

Research Assistant

Dr. Bedi's SAFERR AI Lab, UCF

January 2025 - Present
  • Lead red-teaming initiative for Evo2, a 7B parameter generative bio-foundational model, designing systematic adversarial testing workflows
  • Deploy and benchmark transformer architectures on UCF's HPC cluster using SLURM job scheduling and multi-GPU parallelization
  • Develop automated evaluation pipelines to quantify safety vulnerabilities, measuring attack success rates and model refusal behaviors

Undergraduate Research Assistant

Center for Research in Computer Vision REU, UCF

May 2025 - August 2025
  • Executed 100+ adversarial test scenarios against Evo2 bio-foundation model, establishing empirical evidence for inadequate safety guardrails in generative biology
  • Developed novel jailbreaking methodology achieving 28% higher bypass rate than existing state-of-the-art prompt injection techniques
  • Architected comprehensive evaluation framework with custom metrics for assessing dual-use potential and biosecurity risk in foundation models
  • Continuing post-REU research to formalize safety improvement proposals for bio-foundation AI alignment

TECHNICAL SKILLS

Languages

Python Java C C++ SQL JavaScript

Frameworks

MERN React Native Flutter LangChain LangGraph Flask API REST API

ML / AI

PyTorch TensorFlow Keras RAG Light-RAG CUDA ROCm

Platforms

Linux HPC Git Google Cloud Jira Agile

Bioinformatics

MACS2 HOMER UCSC Genome Browser

LET'S CONNECT

Open to research collaborations, opportunities in AI safety, and healthcare AI projects