Systems

TL;DR — A paged KV cache with grouped-query attention (GQA) sharing and a prefix-reuse eviction policy is one of the most credible LLM-systems projects you can ship to a CV in a weekend. It mirrors the design choices in vLLM, SGLang, and the RadixAttention paper, demonstrates that you understand memory hierarchies, attention math, and eviction, and produces a runnable artifact you can benchmark on real prompts. Why This Project Stands Out on a CV Hiring managers for inference, ML platform, and applied-LLM roles scan portfolios for evidence that a candidate can translate a paper into a working system. A paged KV cache hits that target harder than almost any other weekend project because the design space is genuinely contested in production: vLLM ships PagedAttention, SGLang ships RadixAttention, TensorRT-LLM ships in-flight batching with custom paged kernels, and HuggingFace TGI ships its own block manager. Building one from scratch proves you have read those systems and understood why they look the way they do. ...

How QBE compiles SSA IR to machine code, with a close look at its linear-scan register allocator and the inline caching techniques production JITs use to recover lost megamorphic performance.

Build a production-shaped eBPF/XDP packet classifier from scratch in C. Real code, real architecture, and a clear roadmap to extend it into a senior-level systems project.

Build a runnable LSM-tree key-value store with a write-ahead log in Rust, from WAL append to SSTable flush to compaction. The exact project to make your CV read like a database engineer’s.

Demystify how LLM inference works by building a tiny inference engine from scratch. Covers tokenization, the transformer forward pass, KV cache, and decoding.