# Aidan Do

> LLM Inference Optimization @ Fireworks AI | Nvidia/Meta Open Source Contributor | Ex-Canva

Location: San Francisco Bay Area, United States
Profile: https://flows.cv/aidando

🔹 On the Performance team at Fireworks AI - making inference faster.
🔹 Open-source contributor to NVIDIA (FlashInfer, CUTLASS) and Meta (PyTorch)

## Work Experience
### Software Engineer, Inference @ Fireworks AI
Jan 2025 – Present | San Francisco Bay Area
- Improved VLM inference latency/throughput by 1.6x–2.2x across 3 customer workloads — helping land $_M ARR in new revenue
- Improved TTFT of Kimi K2.5 by 11%–21% for 5–10 image case by writing a custom position embedding bicubic interpolation CUDA kernel — outperforming torch.nn.functional.interpolate by 100x–1700x
- Improved MXFP8 CUTLASS GEMM performance by 10–40% at batch ≤32 via swap ab trick, increasing system-wide tok/s by 4–5% across ___B+ annual output tokens

### NVIDIA/Meta - Open-source Contributor @ NVIDIA
Jan 2026 – Present
Contributor to NVIDIA (FlashInfer, CUTLASS) and Meta (PyTorch) open-source projects:
• PyTorch: Rewrote CUDA upsample_bicubic2d kernel to parallelize across batch and channel dimensions — 4.3-43x speedup for VLM position embedding resizing - https://github.com/pytorch/pytorch/pull/174578

• FlashInfer: Upstreamed FP8 Groupwise GEMM optimization for small-M decode shapes — 10-40% faster at batch ≤32 - https://github.com/flashinfer-ai/flashinfer/pull/2327

• CUTLASS: Fixed SM100 (Blackwell) FP8 profiler bug — corrected epilogue shape_div divisibility condition for non-multiple-of-64 N tiles - https://github.com/NVIDIA/cutlass/pull/2946

### Software Engineer @ Canva
Jan 2024 – Jan 2025 | Sydney, NSW
• Designed and built fraud response service over gRPC, MySQL, DynamoDB, AWS — handling 10–100x projected growth in fraud cases

### Meta AI Open-source Contributor @ Meta
Jan 2024 – Jan 2025
• 7th most active contributor (as of 19 Jan 2024) to official Meta AI projects — Llama-stack/Llama-recipes. Full list of merged PRs: https://bit.ly/4kLbRQm

### Software Engineer @ Semantic Sciences Pty Ltd
Jan 2023 – Jan 2024
Developed and maintained enterprise application managing $800M+ in research funding allocation for Australia's main medical research organization

### Junior Software Engineer @ NQRY
Jan 2021 – Jan 2022 | Adelaide, South Australia, Australia
Maintained a criminal investigation application, implementing mission-critical features for law enforcement organizations

### Software Engineer Intern @ NQRY
Jan 2021 – Jan 2021 | Adelaide, South Australia, Australia


## Education
### Bachelor of Software Engineering (Honours)
University of Adelaide


## Contact & Social
- LinkedIn: https://linkedin.com/in/aidando

---
Source: https://flows.cv/aidando
JSON Resume: https://flows.cv/aidando/resume.json
Last updated: 2026-04-10