Python

A diagram showing tokens being routed to multiple expert networks through a gating mechanism.

Build a Switch-Style MoE Router from Scratch in Pure Python

A hands-on guide to building a Switch-style MoE inference router in pure Python — covering top-k gating, capacity-constrained dispatch, and differentiable load balancing — as a portfolio project that signals real systems ML engineering skill.

From-Scratch GGUF Weight Loader with Blockwise Dequantization, mmap Streaming, and Safetensors Export

A practical guide to implementing a GGUF loader with blockwise dequantization and safetensors export, demonstrating low-level systems expertise.

A conceptual diagram of a paged attention KV-cache architecture showing memory blocks, page tables, and eviction queues.

Build a Pure-Python Paged Attention KV-Cache with LRU and Frequency-Based Eviction

A hands-on guide to building a pure-Python paged attention KV-cache with LRU and frequency-based eviction policies — a portfolio project that demonstrates deep systems engineering skills.

Python code and mathematical formulas representing vector indexing.

Building an IVF-PQ Vector Index from Scratch in Pure Python

Learn how to build an IVF-PQ vector index from scratch using pure Python, implementing k-means clustering and product quantization to achieve scalable similarity search.

Code editor showing a Python-based LLM serving engine implementation

Build a Pure-Python Continuous Batching LLM Serving Engine from Scratch

A hands-on guide to building a pure-Python continuous batching LLM serving engine with PagedAttention KV cache and dynamic batch scheduling — a portfolio project that signals deep systems engineering skill.