Vivek's Field Notes

Topics

Everything I’m working through in AI engineering, LLM serving, backend and distributed systems. One topic at a time, in this order. A topic counts as done only when its proof is done: a number, a demo, or something I can explain without notes.

1. LLM serving basics

Read: Chip Huyen, AI Engineering Ch 9 Β· Raschka, Build an LLM from Scratch Ch 2–4 Β· How to Scale Your Model, inference chapter

2. Continuous batching + paged KV

Read: Huyen Ch 9 (batching) Β· Orca (OSDI ‘22) Β· vLLM / PagedAttention (SOSP ‘23)

3. Go concurrency

Read: Cox-Buday, Concurrency in Go Ch 3–4

4. Kafka + streaming

Read: Kleppmann, DDIA Ch 11

5. Memory, storage, indexes, transactions

Read: DDIA Ch 3, Ch 7 Β· Use The Index, Luke

Read: Huyen Ch 6 (RAG), Ch 7 (finetuning, first part) Β· HNSW paper

7. Agents, tools, context (bigger topic, ~1.5 weeks)

Read: Huyen Ch 2, 5, 6 (agents) Β· Anthropic, Building Effective Agents Β· MCP spec

8. Python concurrency + FastAPI

Read: Fluent Python (2nd ed) Ch 19–21

9. Networking + API resilience

Read: Google SRE book Ch 21–22 Β· High Performance Browser Networking Ch 1–4

10. Containers + Kubernetes

Read: Kubernetes: Up and Running (Pods, Services, Deployments)

11. Replication + partitioning

Read: DDIA Ch 5–6

12. Failures, clocks, consensus (2–3 week block)

Read: DDIA Ch 8–9 Β· Raft paper Β· MIT 6.5840 Raft labs

13. Evaluation (build lands with engine step 6)

Read: Huyen Ch 3–4, Ch 10 Β· Hamel Husain, Your AI Product Needs Evals

14. OS + memory

Read: OSTEP: event-based concurrency + virtual memory chapters

15. Rust

Read: The Rust Book Ch 4, 10, 16, 17

16. Distributed serving

Read: How to Scale Your Model (parallelism, inference) Β· DistServe (OSDI ‘24)

17. RL for LLMs

Read: Nathan Lambert, RLHF Book (free, rlhfbook.com) Β· OpenAI Spinning Up (policy gradients, PPO) Β· InstructGPT, DPO, DeepSeekMath (GRPO) papers

Build: mini inference engine