Over 6 years I've done AI work that reached millions: through research, through open source, through my own products, and through what I delivered to several organisations.

With Vitalops I did LLM inference at scale for a high volume of users, improving token speed and throughput. I also built enterprise automation for large enterprises in supply chain and finance. Prior to that, my engineering stints involved working with organisations to solve some of their hardest challenges.

Along the way I've mentored 10,000+ people on their tech careers.

Resume (PDF)

Abhigith Neil Abraham

📦 Open source

Projects I maintain and the repositories I contribute to, with live star and merged-PR counts, are on the open source page.

📮 Writing

Oct 14, 2026Sleep mode on a Mac: give the KV cache back when vLLM is idle abneil.dev
Oct 13, 2026Get on the leaderboards: benchmark coding agents and increase LLM inference TPS
Sep 28, 2026Learning Inference: a case study for beginners
Sep 25, 2026Learning LLM Inference: confidential computing to keep data private
Sep 22, 2026Learning LLM Inference: scaling from a single node to millions of users
Sep 19, 2026Learning Inference: how to host and improve the token speed of an LLM
Aug 8, 2026A simple practical mental model for LLM inference optimization
May 27, 2026Solving your FOMO in this agentic AI world
Jun 5, 2025Solving complex data pipelines with Composio + Datatune
Apr 24, 2024A very basic roadmap for starting with machine learning and generative AI
Apr 4, 2024Solving your FOMO about everything in LLMs
Mar 27, 2024Data for LLMs: navigating the LLM data pipeline
Feb 19, 2024Real-time object detection using YOLOv8: a step-by-step walkthrough E2E Networks
Feb 5, 2022Sentence embeddings with PyTorch Lightning Paperspace
Oct 25, 2021Solving question-answering on tabular data: a comparison Paperspace
May 7, 2021A comparison of question answering models Paperspace

The rest is on Medium. Papers, talks and older writing are indexed on the blogs and publications page.

📬 Follow me

The best way to reach me is email. I'm also on X, GitHub and LinkedIn.