Shivani .. — Software Engineer

Software Engineer with a strong foundation in Machine Learning, Large Language Models, and scalable backend systems, currently working on production-grade NLP and retrieval systems at an enterprise scale. I specialize in building and optimizing LLM-powered applications, including document summarization, semantic search, RAG pipelines, and multi-modal retrieval systems. My work spans the full ML lifecycle—from data preprocessing and fine-tuning (LoRA/QLoRA) to high-performance inference using ONNX, quantization, and GPU optimization. Previously at Samsung Electronics, I developed high-traffic Python backend services and REST APIs, integrating ML inference pipelines and improving system latency by up to 30%. At Leena AI, I took ownership of core ML modules, deploying large transformer models (T5-Large, LLaMA-2 13B) on 10M+ document corpora, improving retrieval accuracy and inference efficiency in production environments. I bring a strong problem-solving mindset with top-tier competitive programming credentials (CodeChef 6★, Top 0.01%), and hands-on experience across PyTorch, HuggingFace, FastAPI, FAISS, MLflow, Azure & AWS. I’m passionate about: Building efficient, scalable AI systems Turning research ideas into production-ready solutions Optimizing models for real-world performance 📍 Gurgaon, India 📫 Open to ML Engineer / LLM Engineer / Backend-AI roles

Stackforce AI infers this person is a Backend-heavy Fullstack Engineer specializing in Machine Learning and NLP for enterprise applications.

Location: Gurugram, Haryana, India

Experience: 8 mos