AI Systems Engineer
I build systems that run LLMs in the real world—whether that's on a Raspberry Pi, a B200 cluster, or something in between. My focus: making models actually work within real constraints (latency, cost, hardware, privacy).
A custom Sglang fork where I experiment with kernel-level optimizations.
- Exploring FlashAttention memory patterns and adaptive kernel selection
- Practical focus: better throughput without sacrificing flexibility
- Currently used in a few production deployments
- Use CuTeDSL kernels isntead of cutlass cute c++
Helios-Engine – Rust Agent Framework
A lightweight framework for building reliable LLM agents.
- Async I/O with Tokio, zero-copy patterns where it matters
- Built for projects that need control without the Python overhead
Zeroum – VLLM based Inference System
zeroum is a fast and easy-to-use library for LLM inference and serving. Based on vLLM but enhanced with a Rust serving layer that bypasses concurrency limits and allows enterprise-level serving with 1/6 the CPU usage of the Python layer.
The Modular Platform is an open and fully-integrated suite of AI libraries and tools that accelerates model serving and scales GenAI deployments. It abstracts away hardware complexity so you can run the most popular open models with industry-leading GPU and CPU performance without any code changes.
If you're working on inference, kernels, or just trying to ship LLMs without burning a cloud budget—say hi. I'm always up for swapping notes.
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣤⡶⠿⠿⠷⣶⣄⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣰⡿⠁⠀⠀⢀⣀⡀⠙⣷⡀⠀⠀⠀
⠀⠀⠀⡀⠀⠀⠀⠀⠀⢠⣿⠁⠀⠀⠀⠘⠿⠃⠀⢸⣿⣿⣿⣿
⠀⣠⡿⠛⢷⣦⡀⠀⠀⠈⣿⡄⠀⠀⠀⠀⠀⠀⠀⣸⣿⣿⣿⠟
⢰⡿⠁⠀⠀⠙⢿⣦⣤⣤⣼⣿⣄⠀⠀⠀⠀⠀⢴⡟⠛⠋⠁⠀
⣿⠇⠀⠀⠀⠀⠀⠉⠉⠉⠉⠉⠁⠀⠀⠀⠀⠀⠈⣿⡀⠀⠀⠀
⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢹⡇⠀⠀⠀
⣿⡆⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣼⡇⠀⠀⠀
⠸⣷⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢠⡿⠀⠀⠀⠀
⠀⠹⣷⣤⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣀⣰⡿⠁⠀⠀⠀⠀
⠀⠀⠀⠉⠙⠛⠿⠶⣶⣶⣶⣶⣶⠶⠿⠟⠛⠉⠀⠀⠀⠀⠀⠀