Akhil Shekkari

AI Engineer · LLM Inference & Serving · MS Applied ML @ UMD

profile.jpg

University of Maryland

MS Applied Machine Learning

Hi, I’m Akhil. I’m an AI Engineer and earned an MS in Applied Machine Learning at the University of Maryland. Before UMD, I was an AI Engineer at Atrium on a Pfizer R&D project and co-authored a peer-reviewed publication in Clinical Trials. I also spent three years as an ML Engineer at Tezo in India.

My interests include LLM inference and agent systems, with a focus on building practical understanding through hands-on work.

Read my evolving perspectives on general-purpose AI, including multimodal learning, grounded world models, and human-centered systems.

news

Jun 15, 2026 Built Coding Agent, a LangGraph CLI agent with repo-scoped tools and self-hosted vLLM inference.
Jun 01, 2026 Built Mini-vLLM: paged KV cache and continuous batching for single-GPU inference.
Mar 03, 2026 Co-authored a peer-reviewed paper in Clinical Trials with Pfizer R&D. Read the paper.
Feb 01, 2026 Published GPU Fundamentals & LLM Inference Mental Models.

latest posts

selected publications

  1. Leveraging generative AI to transform statistical analysis plan authoring in clinical trials
    Rogier Landman, Birol Emir, Richard Zhang, and 16 more authors
    Clinical Trials, 2026