Portrait of Prathyusha

Hi, I'm Prathyusha Dokku

Machine Learning, Computer Vision & Generative AI Engineer.

About Me

Innovative ML & Generative AI Engineer with 1.5+ years in NLP, Computer Vision, and Deep Learning.

AI concept illustration

My mission is to learn and develop cutting edge algorithms that mimic and eventually exceed human capabilities across vision, speech, audio processing, and more. I believe that since human intelligence exists in nature, we can reverse-engineer and enhance it through technology. Every algorithm I build brings me closer to creating AI systems with truly human-like perception and cognition.

Computer Vision Deep Learning NLP Generative AI PyTorch TensorFlow RAG Systems LLMs

Work Experience

Researcher

School of Computing, SIU Carbondale

ML & Generative AI Engineer

Altiusnxt

Research Assistant

SIU Carbondale

Generative AI Engineer

Manthan Labs

Researcher for Reusable Launch Vehicle

ORBITX INDIA AEROSPACE (P) LTD

Projects Timeline

Image Denoising Using Graph Neural Networks

Mixture-of-Experts framework combining classical filters and deep learning with GNN router, achieving PSNR 40.76 and SSIM 0.944.

AI-Driven AV Perception & Decision-Making

YOLO, U-Net, and RL agents in CARLA for autonomous navigation.

MineTXIM: Multimodal VQA

Built a Retrieval-Augmented Visual Question Answering (RAG-VQA) system that combines image understanding (CLIP) with text retrieval (MiniLM + WIT dataset) using FAISS for large-scale search.

Uncovering Hidden Data in Nighttime Satellite Imagery

GAN Brightener + ViT-FastRCNN dual-architecture for low-light feature detection.

Objeckto: Object Detection & Segmentation

Mask R-CNN & Faster R-CNN on MS COCO.

View Project

Black Friday Sales Prediction

Linear & ensemble regression models achieving R²≈1 for purchase amount forecasting.

View Project

Hello Face: Interactive Recognition

Real-time face detection, recognition & voice feedback with OpenCV, dlib, and Flask.

View Project

Hello Face: Interactive Face Recognition & Registration System

Real-time face recognition system using OpenCV, dlib, and OpenFace for personalized experiences in smart homes and retail.

Education

Education illustration

Master of Computer Science, SIU Carbondale

GPA: 4.0

Bachelor of Computer Science, Osmania University

GPA: 3.26

Certificates

Publications

Yet to be Published

Contact

Email: prathyusha.hyra@gmail.com

Phone: +1 618-818-0226

LinkedIn Google Scholar GitHub