💼 Work Experience
Machine Learning Intern
INDSAC Softech Paid Internship
Eyesense - AI based Surveillance System
• Engineered AI surveillance system across 4 CCTV feeds, automating visitor tracking and reducing manual security checks by ~60%.
• Built face recognition pipeline using Hugging Face FaceNet embeddings and FAISS vector indexing, achieving sub-100ms matching for
500+ profiles.
• Developed OpenCV real-time video pipeline processing concurrent streams at 25 fps with zero frame drops for continuous detection
and tracking.
• Designed automated alert engine notifying admins via SMS/email within 3 seconds of detecting unauthorized individuals.
• Built and containerized Flask web platform using Docker for visitor approvals, real-time access logging, and system monitoring.
Machine Learning Research Intern
Suvidha Foundatation Full Time
Mulit-News Summarization in Indian English
• Researched multi-document summarization for Indian English using LLMs, benchmarking 15+ architectures (T5, BART, PEGASUS,
LLaMA).
• Fine-tuned Llama 3-3B with 4-bit QLoRA using Hugging Face PEFT, achieving a 49.06 ROUGE-1 score—outperforming the PEGASUS
baseline by 6.2 points.
• Designed 4-bit quantization pipeline enabling large-model fine-tuning on a single T4 GPU, cutting memory usage by ~40% vs full fine
tuning.
• Benchmarked LoRA vs. QLoRA performance across speed, memory, and accuracy, achieving 3x lower compute consumption while
tracking experiments in MLflow.
🎓 Education
Master of cComputer Application - Computer Application
Devi Ahilya Vishwavidyalaya, Indore
2024 - 2026
Bachelor of Computer Applications - Computer Applications
Devi Ahilya Vishwavidyalaya, Indore
2021 - 2024
Skills & Expertise
About
Machine Learning Engineer with hands-on experience in building and deploying AI-driven systems across Computer Vision and NLP domains. Skilled in developing real-time applications, implementing LLM-based solutions, and optimizing models using techniques like PEFT (QLoRA, LoRA). Proven ability to design end-to-end ML pipelines, from data processing to deployment, with a focus on scalable and efficient solutions.