@bytebuzz
Soumili Saha
@bytebuzz
A passionate student with a keen interest in Data Science and Data Analysis and bioinformatics. I specialize in Machine Learning, NLP, and Generative AI.
A passionate student with a keen interest in Data Science and Data Analysis and bioinformatics. I specialize in Machine Learning, NLP, and Generative AI.
Kolkata, India
Hello, I am Soumili Saha, a second-year B.Tech student in the Computer Science and Engineering department at B.P. Poddar Institute of Management and Technology. I am proficient in Java and Python, and my journey in tech has involved developing advanced machine learning models, working with NLP and LLMs, generative AI, Image processing, and, most recently, bioinformatics.
Some of my notable projects include:
Career Catalyst – An AI-powered job and career guidance platform with features like skill-gap analysis, dynamic mapping, resume parsing, and personalized job recommendations.
PathoPredict – An ML model of predicting pathogenicity of genetic variants using a gradient boosting mechanism trained on a large ClinVar dataset. This work achieved a significant rate of accuracy of 93.75 % and is currently submitted to AISC 2025 for publication.
SafeWalk – A real-time pedestrian safety alert system using computer vision and sensors to prevent accidents by detecting mobile distractions in high-risk zones.
I am passionate about solving real-world problems through innovation and have actively participated in various hackathons and competitions:
ICDMAI 2025 Finalist
GSSOC Contributor 2024
Intra College Hackathon Winner
Internal SIH Position Holder
Kshitij IIT Kharagpur Campus Ambassador
GDSC Core Member (2024 - Present)
I’ve earned certifications from NPTEL and Coursera in Machine Learning, Deep Learning, Genomic Data Science, and more. With full professional proficiency in English, Hindi, and Bengali, I enjoy exploring cross-domain challenges that blend healthcare, AI, and real-time systems.