Harshit Shah

B.Tech Student in Bioengineering | AI & Genomics Researcher

Email | Phone | LinkedIn

[email protected]

+918275566293

Pune, IN

About

Highly motivated B.Tech student in Bioengineering with a strong foundation in AI-driven genomics, biomedical image analysis, and data science. Proven ability to develop automated pipelines, analyze complex biological datasets, and contribute to research insights in cancer biology and real-time gene data retrieval. Seeking to leverage expertise in Python, R, Java, and deep learning frameworks to innovate within the biotechnology and healthcare sectors.

Work Experience

Project Research Intern

1Cell.Ai

Jan 2025 - Jun 2025

Pune, Maharashtra, IN

As a Project Research Intern, Harshit automated multi-channel cancer cell image analysis, significantly enhancing throughput and accuracy for circulating tumor cell evaluation.

  • Automated multi-channel cancer cell image analysis using custom ImageJ macros and Java plugins, enabling high-throughput evaluation of circulating tumor cells (CTCs).
  • Integrated per-cell intensity measurement, morphological analysis (area, circularity), and karyoplasmic ratio calculations into a single reproducible pipeline, ensuring data consistency.
  • Reduced manual processing time from 7 minutes to 3 seconds per image by developing a fully automated workflow with Bio-Formats and ROI-based quantification, improving both speed and accuracy by over 50%.

Summer Project Intern

Bioinformatics Centre, SPPU

Jul 2024 - Sep 2024

Pune, Maharashtra, IN

As a Summer Project Intern, Harshit conducted comprehensive genomic dataset analysis and developed automated pipelines for data wrangling and visualization in cancer biology research.

  • Conducted preprocessing and analysis of genomic datasets using Python and R, focusing on gene expression and mutation profiling relevant to cancer biology research.
  • Developed robust pipelines for automated data wrangling and visualization, including clustering, differential expression, and pathway enrichment analysis for genomic datasets.
  • Collaborated with researchers to interpret complex bioinformatics results, contributing to integrative insights in cancer genomics and supporting experimental validation.

Education

Bioengineering

MIT ADT University

Aug 2021 - Jul 2025

Pune, Maharashtra, IN

Projects

Genetics-GPT – AI-Powered Genomics Question Answering System

Designed and deployed an AI-driven Question Answering system for genomics, leveraging large language models and biomedical APIs to provide real-time data retrieval and analysis.

Awards

Finalist at NABARD Rural Innovation Hackathon

NABARD

Jan 2024

Recognized as a finalist in the national innovation hackathon, demonstrating innovative problem-solving skills and a commitment to rural development.

Skills

Programming Languages

  • Python
  • R
  • Java
  • SQL

Data Science & Machine Learning

  • PyTorch
  • TensorFlow
  • Keras
  • Scikit-learn
  • OpenCV
  • Pandas
  • NumPy
  • Matplotlib
  • Seaborn
  • NLP
  • AI-driven QA Systems
  • Genomics Data Analysis

Development Tools & Platforms

  • PyCharm
  • Jupyter Notebook
  • Google Colab
  • VS Code
  • Git
  • GitHub
  • Docker
  • ImageJ

Bioinformatics & Biomedical Imaging

  • Genomic Datasets
  • Gene Expression Analysis
  • Mutation Profiling
  • Pathway Enrichment Analysis
  • Cancer Cell Image Analysis
  • Circulating Tumor Cells (CTCs)
  • Bio-Formats
  • ROI-based Quantification
  • Biomedical Entity Linking