AI Systems · Inference engineering · Distributed systems · LLMOps · Infra engineering

Abi Aryan

My philosophy

Don't accept the abstraction.

Understand what the system actually does. Take it apart. Measure it. Build your own mental model from the evidence.

Hi, I am Abi! I am an AI Infrastructure Engineer building inference systems for data centers, neoclouds, and hyperscalers. I founded Joule, an inference power economics engine that ties physical GPU energy to token throughput and SLO goodput.

I build the systems, measure them, research them, write about them, and teach them. The path, the books, and the research sit on About.

I built this

Here is the code →
  • Company Joule

    Founder. Joule is an inference power economics engine that ties physical GPU energy to token throughput and SLO goodput.

  • Curriculum gpuengineering.com

    The public list behind the domain: CUDA, kernels, serving engines, multi-GPU systems. ~600 stars as awesome-gpu-engineering.

  • Serving RelayServe

    Minimal LLM inference gateway for heterogeneous devices. OpenAI-compatible chat, batching, streaming, request IDs, /metrics. On PyPI as relayserve.

  • Engine smol-vllm

    Educational paged-attention engine: KV cache, continuous batching, preemption, prefill vs decode. Built to be read, not shipped as production vLLM.

  • Lab / Lambda fullstack-inferencing

    vLLM on Lambda Cloud, FastAPI gateway, nginx, Prometheus, Grafana, optional Jaeger. Documents engine-flag limits, cost metrics, and Lambda image caveats.

I measured this

Here is what I found →

On Writing: Investigations, Archive, ModelCraft, Field notes.

From the cohorts

Maven courses →

“This course was very helpful in giving me a broad, end-to-end understanding of the LLM inference space and connecting the key concepts.”

Vijay · Lead Member of Technical Staff, Salesforce · July 2026

“It goes beyond theory and dives into the practical challenges of building and scaling LLM inference systems, from KV cache to admission control.”

Anuj · Sr. Machine Learning Engineer · July 2026

“I would give this course 10 stars if I could. We built every part of the inference stack by hand, so we came out understanding the mechanics, not just the APIs.”

Sachin · Founder, Chortle Labs · July 2026

“Fantastic course for deep-diving into LLM systems. The final project covers the full inference lifecycle: load balancing, agentic systems, and observability.”

Vivian · Software Engineer, Google · February 2026

1:1 mentorship

Topmate · 5.0 →

“I got some truly insightful suggestions on my career path during my 1:1 with Abi. I woke up the next morning with absolute clarity on what I need to tackle next.”

Manjunath Yelipeta · Topmate

“I have had few calls through Topmate and she is legit the best I have talked to so far!”

Gokulakannan S · Topmate

“An insightful session on transitioning into the inference side of LLMs, and the gaps in my resume I need to fill.”

Mentee · Topmate
  • Company Joule

    An inference power economics engine that ties physical GPU energy to token throughput and SLO goodput.

    Go to joule.lat

  • Books LLMOps, and GPU Engineering

    LLMOps, written 2023-2024, finished December 2024, published 2025, now in English and four translations. GPU Engineering is almost finished, launch is end of 2026 or early 2027.

    See the books