Cheeni Labs

• Fine-tuned a pre-trained General Embedding model for movie review classification
• Pre-processed and optimized a 100,000-review dataset for training through a BERT-based model for a summary classifier for their product, Flixjini
• Tools: Python, SQL, Sentence Transformers

Prasath Lab, University of Cincinnati

• Developed hybrid feature extraction techniques to enhance brain tumor classification in medical imaging
• Built deep learning models to improve context-based retrieval accuracy for brain tumor images
• Tools: Python, TensorFlow, OpenCV

Gerstein Lab, Yale University

• Trained CNN and Autoencoder models for structural variant classification in gene sequences
• Preprocessed sequences and created embeddings for accurate classification
• Tools: Python, TensorFlow, Hugging Face

ItTrident

• Created an interactive Power BI dashboard analyzing airline operations and passenger behavior
• Built a CRM app in Power Apps to manage customer data, track leads, and automate follow-ups
• Tools: MS Excel, Power BI, Power Apps

Ericsson

• Built a semi-supervised anomaly detection pipeline for time-series KPI data using decomposition techniques and ML models
• Applied causal inference to estimate the causal effect of network configuration parameters on user throughput
• Curated a 10k-sample QA dataset and fine-tuned DeepSeek-R1 distilled models with instruction-tuned prompts for domain adaptation
• Tools: Python, Scikit-learn, Statsmodels, TensorFlow, DoWhy, Hugging Face, Amazon SageMaker

Languages

Python

R

SQL

C++

Shell Scripting

Libraries

NumPy

Pandas

Matplotlib

Seaborn

OpenCV

NLTK

scikit-learn

Frameworks

Streamlit

TensorFlow

Keras

PyTorch

Django

Flask

Other

MySQL

SQLite

Git

Power BI

Tableau

MS Excel