AI Engineer · ML Researcher
Low-level systems and machine intelligence: inference engines, GPU kernels, small models.
| Project | What it is | Stack | Year |
|---|---|---|---|
| mini‑vllm | PagedAttention with Triton kernels, prefix caching and continuous batching | 2025 | |
| gemm‑optimization | SGEMM on an A100: 0.29 → 9.6 TFLOPS, against cuBLAS | 2025 | |
| flash‑attention | FlashAttention 2 from scratch in CUDA | 2024 | |
| rl‑wordle | SFT and RL on Qwen3-1.7B. Wins on held-out words: 0% to 13% | 2026 | |
| nanohunch | Qwen3-4B with LoRA that answers in calibrated probabilities, not text | 2026 | |
| anki‑cli | Anki from the terminal, for humans and agents | 2026 |
More: engram · mhc · tangent · void · Flash · pycc · clox
| Area | Tools |
|---|---|
| ML | |
| Languages | |
| Backend | |
| Infra & data |
Also: JAX · Triton · vLLM · LangGraph · Google ADK · Faiss

