Door categorieën bladeren
Ontdekken
Fiverr Pro
Nederlands
$
USD
Shyam
@shyam_ranasara
Machine Learning Enigneer
India
Engels
Over mij
Hi! I’m Shyam, a Machine Learning Engineer specializing in AI, Computer Vision, NLP, and Generative AI. I build practical AI solutions including ML models, computer vision systems, LLM applications, RAG systems, and model fine-tuning. I work with Python, PyTorch, TensorFlow, OpenCV, YOLO, Hugging Face, LangChain, FAISS, Flask, and FastAPI. I focus on reliable, efficient, and customized solutions that turn your ideas into working products.
Skills
Shyam
offline •
Gemiddelde reactietijd: 1 uur
Bekijk mijn diensten
Machine learning
I will build, fine tune, and deploy custom machine learning and llm models
Computer vision
I will build custom computer vision, object detection, and face rcognition models
Werkervaring
Machine Learning Intern
Indsac • Fulltime
Feb 2026 - Present • 7 mos
Engineered an AI-based surveillance system for real-time visitor monitoring and security automation, reducing manual security check load by ~60% across 4 active CCTV feeds. Built a face recognition pipeline using HuggingFace FaceNet embeddings and FAISS vector indexing, achieving sub-100ms identity matching for 500+ profiles. Developed a real-time video pipeline in OpenCV to detect, track, and capture snapshots at 25 fps, handling concurrent streams without frame drops. Designed an automated alert engine flagging unrecognized individuals within 3 seconds, integrated with SMS and email notifications. Developed a Flask-based web application for visitor approval, access logs, and system monitoring; containerized using Docker.
Machine Learning Research Intern
Suvidha Foundation • Fulltime
Dec 2025 - Feb 2026 • 2 mos
Researched multi-document summarization 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, outperforming PEGASUS baseline by 6.2 points. Designed 4-bit quantization pipeline enabling large-model fine-tuning on a single T4 GPU, cutting memory usage ~40% vs full fine-tuning. Benchmarked LoRA vs QLoRA across speed, memory, and ROUGE metrics; QLoRA delivered 3x lower compute vs full fine-tuning; tracked experiments using MLflow.
