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

AI Engineer specialising in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI systems. Experienced in fine-tuning LLMs using LoRA and RLHF, and building end-to-end ML pipelines on AWS. Developed AI-driven solutions for document analysis and workflow automation, improving efficiency and reducing manual effort. Strong focus on delivering production-ready systems using PyTorch, Hugging Face, and modern MLOps practices.…AI Engineer specialising in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI systems. Experienced in fine-tuning LLMs using LoRA and RLHF, and building end-to-end ML pipelines on AWS. Developed AI-driven solutions for document analysis and workflow automation, improving efficiency and reducing manual effort. Strong focus on delivering production-ready systems using PyTorch, Hugging Face, and modern MLOps practices.

Yash Mathur





AI Engineer specialising in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI systems. Experienced in fine-tuning LLMs using LoRA and RLHF, and building end-to-end ML pipelines on AWS. Developed AI-driven solutions for document analysis and workflow automation, improving efficiency and reducing manual effort. Strong focus on delivering production-ready systems using PyTorch, Hugging Face, and modern MLOps practices.…AI Engineer specialising in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI systems. Experienced in fine-tuning LLMs using LoRA and RLHF, and building end-to-end ML pipelines on AWS. Developed AI-driven solutions for document analysis and workflow automation, improving efficiency and reducing manual effort. Strong focus on delivering production-ready systems using PyTorch, Hugging Face, and modern MLOps practices.

Available to hire

AI Engineer specialising in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI systems. Experienced in fine-tuning LLMs using LoRA and RLHF, and building end-to-end ML pipelines on AWS. Developed AI-driven solutions for document analysis and workflow automation, improving efficiency and reducing manual effort. Strong focus on delivering production-ready systems using PyTorch, Hugging Face, and modern MLOps practices.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

AI Engineer at Orcawise

June 1, 2025 - Present

Fine-tuned Llama-based LLMs using SFT and LoRA for legal document analysis using internal evaluation benchmarks. Integrated a reward model for ranking LLM outputs to improve consistency and reduce low-quality generations during RLHF training. Applied reinforcement learning methods (PPO, GRPO) on AWS SageMaker to improve model alignment and reduce hallucinations. Designed and deployed an agentic AI system automating legal document analysis workflows, reducing manual effort by ~30%. Built a RAG pipeline using embeddings and similarity-based retrieval over a 10k+ document corpus to improve retrieval relevance and answer quality. Managed ML infrastructure on AWS (SageMaker, EC2, S3, Lambda) and improved turnaround time for experimentation. Reduced document analysis time from ~8–10 minutes to ~3–4 minutes per document and used Weights & Biases for experiment tracking and reproducibility.

Machine Learning Intern at HCL Technologies

January 1, 2024 - May 1, 2024

Built a RAG system using LlamaIndex and MongoDB. Developed AWS-based ingestion and preprocessing pipelines including embedding generation and storage using S3 and EC2. Designed embedding workflows for scalable document retrieval, improving retrieval accuracy by 15% through iterative tuning and evaluation. Optimised system performance for faster response times and scalability.

Data Science Intern at TCS - Tata Consultancy Services

May 1, 2023 - July 1, 2023

Developed a recommendation system using Random Forest, XGBoost, and LightGBM, improving F1 score by 11% and increasing user engagement by 8%. Built ML pipelines on AWS (SageMaker, Lambda, S3) for automated training and inference. Implemented CI/CD workflows using GitLab and processed large datasets using SQL and Snowflake.