Machine Learning Engineer specializing in Large Language Models and inference optimization. Experienced in fine-tuning L

substack

medium

github

Semil periysamy  • Peerlist

Production-grade LLM deployment system optimizing inference and training at scale. Key Achievements: • Reduced inference latency from 2.5s to 450ms (82% improvement) using quantization, batching, and vLLM optimization • Implemented PEFT/QLoRA fine-tuning enabling 70B+ parameter models on consumer-grade GPUs • Reduced deployment costs by 40%+ through resource optimization and auto-scaling strategies • Deployed 3+ production models with 98%+ uptime on Azure ML infrastructure • Built automated retraining pipelines reducing manual intervention by 80% • Multi-GPU training optimization achieving 2-3x speedup improvements Tech Stack: PyTorch, CUDA, vLLM, Azure ML, Docker, Kubernetes, Redis

LLM Infrastructure Optimization & Deployment

Using CNN algorithm ,we predict the eye disease using a mobile application with the use of mobile camera

Multiple Eye disease detection system using C

Engineered intelligent NLP-based chatbot for room reservations using LLaMA 2 with context awareness. Integrated real-time availability updates with REST APIs and WebSockets. Designed RAG pipeline to reduce hallucinations by 65% vs baseline LLM. Production-ready deployment with optimized response latency.