Open to opportunities

Rupal Bula

@rupalbula

Junior Research Fellow applying Python, machine learning, and deep learning to genomics and data-driven backend services.

India

Message

What I'm looking for

I’m looking for a collaborative team where I can apply Python, ML/DL, and bioinformatics or audio/data-science workflows—building reliable pipelines and services—to solve real-world problems and grow through continuous learning.

I’m a Junior Research Fellow working on soybean genomics and large-scale SNP data analysis with the Soy50K dataset. I design and implement data processing pipelines for HapMap/TXT genomic datasets, and I build FastAPI-based backend services to enable genome data querying and analysis.

I also integrate JBrowse with custom backend APIs for interactive genome visualization, and I develop sequence search tools and utilities for SNP comparison and dataset transposition. Previously, as a Junior Data Scientist, I built a speaker identification system using an audio preprocessing pipeline and MFCC-based Gaussian Mixture Models, then evaluated how preprocessing choices impacted identification accuracy and model performance—while staying committed to continuous learning, problem-solving, and collaborative teamwork.

Experience

Work history, roles, and key accomplishments

Current

Junior Research Fellow

Current

ICAR–National Soybean Research Institute (ICAR-NSRI)

Jul 2025 - Present (1 year 1 month)

Worked on soybean genomics and large-scale SNP data analysis using the Soy50K dataset, including building genomic data processing pipelines and tools. Developed FastAPI-based backend services and integrated JBrowse for interactive genome visualization, plus implemented sequence search and SNP comparison utilities.

Soy50K Dataset Genetic Variant Data Data Pipelines fastAPI Backend Services JBrowse Integration Sequence Search PROC TRANSPOSE SNP Similarity Analysis

Junior Data Scientist

TekStitcher IT Services Pvt Ltd

Dec 2023 - Jun 2025 (1 year 6 months)

Developed a speaker identification system using audio characteristics and built an audio preprocessing pipeline including noise reduction, silence removal, and feature extraction. Trained and evaluated Gaussian Mixture Models using MFCC and related features, and analyzed the impact of preprocessing on identification accuracy.

Speaker Identification Audio Processing Silence Removal MFCC Feature Extraction Delta MFCC Delta Delta MFCC Gaussian Mixture Model Model Evaluation Accuracy Audio Signal Processing

Education

Degrees, certifications, and relevant coursework

Shri Govindram Seksaria Institute of Technology and Science

M.Tech (Computer Engineering), Computer Engineering

2022 - 2025

Grade: CGPA: 7.46

Completed an M.Tech in Computer Engineering at Shri Govindram Seksaria Institute of Technology and Science from 2022 to 2025, achieving a CGPA of 7.46.