Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a Machine Learning Engineer with an MCA from Devi Ahilya Vishwavidyalaya, Indore. I specialize in production AI, ML model fine-tuning, and real-time video analytics. I have completed two research internships, fine-tuned Llama 3 via QLoRA achieving ROUGE-1 49.06, and built CCTV face recognition pipelines using HuggingFace embeddings + FAISS, OpenCV-based video pipelines, and Flask services.…

Shyam R Anasar

AI Engineer, AI Developer, Data Scientist, +2





I am a Machine Learning Engineer with an MCA from Devi Ahilya Vishwavidyalaya, Indore. I specialize in production AI, ML model fine-tuning, and real-time video analytics. I have completed two research internships, fine-tuned Llama 3 via QLoRA achieving ROUGE-1 49.06, and built CCTV face recognition pipelines using HuggingFace embeddings + FAISS, OpenCV-based video pipelines, and Flask services.…

Available to hire

I am a Machine Learning Engineer with an MCA from Devi Ahilya Vishwavidyalaya, Indore. I specialize in production AI, ML model fine-tuning, and real-time video analytics.

I have completed two research internships, fine-tuned Llama 3 via QLoRA achieving ROUGE-1 49.06, and built CCTV face recognition pipelines using HuggingFace embeddings + FAISS, OpenCV-based video pipelines, and Flask services.

Skills

Experience Level

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

Machine Learning Intern at INDSAC Softech

February 1, 2026 - Present

Engineered an AI-based surveillance system for real-time visitor monitoring across 4 CCTV feeds; built a face recognition pipeline using HuggingFace FaceNet embeddings and FAISS with sub-100ms identity matching for 500+ profiles; developed a real-time OpenCV-based video pipeline at 25 fps for multi-camera streams with no frame drops; designed an automated alert engine notifying security and management within 3 seconds of detecting an unrecognized individual via SMS and email; built a Flask web app for visitor approvals, access logs, and monitoring; containerized with Docker for reproducible deployment across environments.

Machine Learning Research Intern at Suvidha Foundation

December 1, 2025 - February 28, 2026

Researched multi-document summarisation for Indian English using LLMs; surveyed 15+ architectures (T5, BART, PEGASUS, LLaMA) to inform model selection; fine-tuned Llama 3-3B using QLoRA (4-bit) via HuggingFace PEFT library, achieving ROUGE-1 49.06; designed a 4-bit quantisation pipeline enabling large-model fine-tuning on a single T4 GPU, cutting memory usage ~40% vs full fine-tuning; tracked experiments with MLflow for reproducibility; benchmarked LoRA vs QLoRA across speed, memory, and ROUGE metrics.