Hire Shivani B. - LLM Engineer

About shivani

I’m a Machine Learning Engineer specializing in building production-grade NLP and LLM systems—from fine-tuning large transformer models to optimizing inference for real-world scale and latency constraints. Currently, I work as a Junior ML Engineer, where I design and deploy document summarization, semantic search, and multi-modal retrieval systems using models like T5-Large and LLaMA-2, fine-tuned with LoRA/QLoRA on large-scale corpora (10M+ documents). My work focuses heavily on model efficiency and reliability, leveraging ONNX optimization, quantization (8-bit/4-bit), graph fusion, and GPU optimization, achieving measurable gains in latency, throughput, and memory usage. Previously, I’ve worked as a Python Developer (ML/AI), building Generative AI-powered ERP modules, FAISS-based semantic search engines, and deploying scalable ML systems on Azure ML, Kubernetes, and AWS. I enjoy working across the ML lifecycle—data pipelines, training, evaluation (BLEU, ROUGE, Perplexity), deployment, and monitoring—with strong emphasis on clean, production-ready code. Beyond work, I’m an active competitive programmer (6 CodeChef, top 0.2% globally) with a strong algorithmic foundation that helps me reason about performance, scalability, and system design. Core Interests: LLMs & NLP * Retrieval-Augmented Generation (RAG) * Model Optimization * MLOps * Applied AI Systems Tech Stack: Python, PyTorch, HuggingFace, FastAPI, FAISS, ONNX, Azure ML, AWS, MLflow, Docker I’m passionate about turning cutting-edge ML research into reliable, scalable products and always open to discussions around AI engineering, NLP systems, and real-world ML challenges.

Common Questions

Other LLM Engineers