Teaching · Maven
From AI engineer to inference engineer.
I teach popular, highly rated masterclasses on Maven: AI Inference Engineering & Systems Design for mid-to-senior engineers, and AI Inference for FDE and PM Roles. 1.7K subscribers, amongst the top-most rated instructors on Maven. Six free lightning lessons, and the live cohort.
Invited Faculty for AI Inference Engineering at Andreessen Horowitz Academy (The Academy SF).
On Maven
Maven school →- AI Inference Engineering & Systems Design
A highly rated masterclass for mid-to-senior engineers. Build the stack by hand. Next live cohort 24 Oct - 19 Dec 2026.
- AI Inference for FDE and PM Roles
A masterclass on what is happening inside the model, for FDE, PM, and adjacent technical roles.
Lightning lessons (Slides)
Watch on Maven →The ladder
- LinkedIn
The question. A folk model, then a contradiction.
- Maps
The stack. Save this, come back in six months.
- ModelCraft
The deep dive. Underutilized GPUs as an economic systems problem.
- gpuengineering.com
What to read, in order.
- GitHub
RelayServe, smol-vllm, the Lambda lab. Run the argument.
- Book
The reference that outlives a feed.
- Maven
Popular, highly rated masterclasses: Inference Engineering for mid-to-senior engineers, and Inference for FDE and PM roles.
- 1:1 mentorship
Topmate. Career path into inference. 5.0 from 3 ratings.
From the cohorts
Reviews on Maven →“This course was very helpful in giving me a broad, end-to-end understanding of the LLM inference space and connecting the key concepts. I also really liked Abi Aryan’s teaching style. She makes time for questions and prioritizes student understanding over simply covering the material.”
“This course has been a great learning experience. It goes beyond theory and dives into the practical challenges of building and scaling LLM inference systems, from KV cache management and batching to concurrency, routing, and admission control. The hands-on labs and real-world examples helped me connect the concepts to actual production systems.”
“I would give this course 10 stars if I could !! Abi is an outstanding instructor. She knows the AI inference stack in depth, both at the level of how the pieces actually work and where the industry is heading. Throughout the cohort she went out of her way to make sure we understood the material. We built every part of the inference stack by hand in this course, so we came out understanding the mechanics, not just the APIs. It is very hands-on. If you work through the homeworks diligently, you will learn more than from any other course I have seen on this topic. The guest sessions with engineers from leading inference companies were a bonus. If you are an engineer in the AI space and want to build your own local or cloud inference stack, or start your own business, I highly recommend this course.”
“Fantastic course for deep-diving into LLM systems. Each week features a great mix of lectures and code demos, supported by detailed documentation. The final project is a highlight, covering the full inference lifecycle: load balancing, agentic systems, and observability with metrics/traces. Abi is a dedicated instructor who truly listens to student feedback. The 1:1 career guidance and system design sessions make this an incredible value for infrastructure-focused engineers.”
1:1 mentorship
5.0 · 3 ratings on Topmate →Sixty minutes. How to find the role in inference, resume gaps, the path, what to learn next. Book 1:1 career mentorship on Topmate.
“I got some truly insightful suggestions on my career path during my 1:1 with Abi. It felt amazing to wake up the next morning with absolute clarity on what I need to tackle next. Thanks for such a wonderful session, Abi! I can't wait to read your Packt book”
“I have had few calls through Topmate and she is legit the best I have talked to so far!”
“The depth of knowledge and the path provided by her was really great. It was an insightful session where I learned the details about transitioning into the inference side of LLM's and the gaps in my resume which I need to fill. Thanks again for this.”