Prashant C.

Key Skills

Software

AWS SageMaker

Google Cloud Vertex AI

Labelbox

Mindrift

Micro1

Mercor

Roboflow

Scale AI

Toloka

Top Subject Matter

Fetal ultrasound image analysis / medical imaging

Agricultural vision / plant disease prediction

Top Data Types

Image

Video

Audio

Top Task Types

Segmentation

Classification

Evaluation/Rating

Computer Programming/Coding

Fine-tuning

Text Summarization

Object Detection

Bounding Box

Data Collection

Function Calling

Prompt + Response Writing (SFT)

Question Answering

Text Generation

Freelancer Overview

Feto-Scan—AI Fetal Analysis Tool (AI/ML image segmentation) Jan2024–May2024. Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include OpenCV and TensorFlow. Education includes Bachelor of Technology (B.Tech.), Bennett University (2022) and Higher Secondary Certificate (ISC), St. Mary’s School (2021). AI-training focus includes data types such as Medical, DICOM, and Image and labeling workflows including Segmentation and Classification.

Labeling Experience

Crop Disease Prediction System Sep2024–Dec2024

ImageClassification

Trained a crop disease prediction model using a dataset of plant images. The project applied a CNN-based approach to learn disease-related patterns and evaluate performance on validation data. The trained model was deployed as a scalable application for concurrent prediction requests. • Trained CNN model on 10,000+ plant images • Achieved 95% validation accuracy • Containerized the ML application with Docker for reproducible environments • Deployed on AWS App Runner to support concurrent prediction requests

2024 - 2024

Feto-Scan—AI Fetal Analysis Tool (AI/ML image segmentation) Jan2024–May2024

Segmentation

Built an AI fetal analysis tool that used an image segmentation model to measure the fetal head region. The work focused on computer-vision preprocessing of ultrasound images and training a CNN to achieve overlap accuracy. Model outputs were intended to automate manual caliper measurements for faster clinical analysis. • Developed an image segmentation pipeline for fetal head measurement • Trained a CNN model achieving 85% IoU • Preprocessed 2,000+ ultrasound images with OpenCV for noise reduction and contrast enhancement • Automated manual caliper measurement workflows to reduce analysis time by 70%

2024 - 2024

Education

Work History