Hi, I’m Akhil!
I am an AI Engineer and an MS student in Applied Machine Learning at the University of Maryland, College Park. Before UMD, I worked as an AI Engineer at Atrium on a Pfizer R&D project, where I co-authored a peer-reviewed publication in Clinical Trials (SAGE), and spent three years as a Machine Learning Engineer at Tezo in India.
My work focuses on LLM inference. I build serving systems from scratch: custom Triton kernels, paged KV-cache, speculative decoding, and distributed orchestration with NVIDIA Dynamo.
University of Maryland
MS Applied Machine Learning
News
- Feb 2026 Built and benchmarked a distributed LLM serving stack with NVIDIA Dynamo, studying disaggregated prefill/decode and KV-aware routing.
- Feb 2026 Published a deep dive on GPU Fundamentals & LLM Inference that reached 15k+ people on LinkedIn.
- May 2025 Co-authored a peer-reviewed publication in Clinical Trials (SAGE) on using generative AI to automate statistical analysis plan authoring at Pfizer R&D. Read ↗