Hi, I'm Partha 👋
Partha Sai Guttikonda is a software engineer and researcher passionate about leveraging machine learning to solve impactful problems in healthcare and beyond
GPS

About

I am a passionate machine learning enthusiast and software engineer with a Master’s degree in Computer Engineering 🎓 from the University of Texas at Arlington, where my research focused on multimodal algorithms, Vision Language Models (VLMs), and 3D modalities for medical applications; I have contributed to cutting-edge research projects, including 🧪 developing a 3D visualization platform for multiplexed immunofluorescence imaging, ⚔️ conducting adversarial attacks on Vision Language Models for pathology to improve AI robustness, and 🩺 building a digital pathology viewer integrated with deep learning-powered search engines; I also gained valuable experience working at Vantashala, a Texas-based startup, where I worked on full-stack development using Vue.js and Java Spring Boot; outside of work, I enjoy photography 📸 and sharing my stories on 👉 Unsplash; this portfolio reflects my journey, projects, and aspirations—let’s connect and collaborate! 🌟📩

Skills

Node.js
Python
Java
C++
Go
Postgres
MongoDB
ElasticSearch
Docker
Kubernetes
AWS
CI/CD
Java Spring Boot
TensorFlow
PyTorch
CoreML
React
Next.js
Typescript
Vue.js
Swift
SQL
My Projects

Check out my latest work

I've worked on a variety of projects, from simple websites to complex web applications. Here are a few of my favorites.

SpatialVisVR

Developed a 3D medical image viewer integrated with contextual similar-patient search, leveraging advanced Vision Language Models to assist pathologists in comparing imaging data.

Python
TensorFlow
PyTorch
CellPose
DGX A100

Automated H&E Detection

Built an AI-based tool to detect and extract H&E images from whole slide photos using ResNet-50, achieving 0.7-second inference times through CoreML integration.

CoreML
ResNet-50
Python

GPU Monitoring System

Implemented GPU monitoring and alert systems using Prometheus and Grafana, optimizing resource allocation for AI workloads.

Prometheus
Grafana
Python
Publications

I like building things

During my time in university, I worked on 3+ papers.

  • A

    Adversarial Attacks on Vision Language Models in Pathology Imaging

    Demonstrated the vulnerabilities of Vision Language Models (VLMs) in pathology imaging by implementing adversarial attacks, highlighting the sensitivity of AI models and proposing strategies for improving robustness.Adversarial Attacks on Vision Language Models in Pathology Imaging
  • D

    Diagnostic Integrity Meets Efficiency: Architecture for Physiological Signal Compression

    Designed an architecture for efficient compression of physiological signals, enabling significant storage savings without compromising diagnostic quality.Diagnostic Integrity Meets Efficiency: Architecture for Physiological Signal Compression
  • M

    Multiplexed Medical Image Viewer with Contextual Similar-Patient Search

    Developed a medical image viewer integrated with a contextual similar-patient search engine, leveraging Vision Language Models to enhance the analysis of multiplexed medical images.Multiplexed Medical Image Viewer with Contextual Similar-Patient Search
Contact

Get in Touch

Want to chat? Just shoot me a dm with a direct question on LinkedIn and I'll respond whenever I can. I will ignore all soliciting.