I'm a systems-first AI engineer. Instead of focusing only on models, I focus on what makes them run efficiently in production: distributed GPU orchestration, KV-cache routing, compiler-level cost prediction, and low-level Rust performance.
- 🎓 Bachelor's degree in Artificial Intelligence, currently completing a Master's in Data Science & Artificial Intelligence
- 🦀 Rust systems builder — from neural networks written from scratch to sub-100µs trading engines, with zero unnecessary Python runtime dependency
- ⚙️ Currently MLOps Engineer at Adorsys
- 🧮 Building NEURAX, an analytical compiler that predicts FLOPs/VRAM/cost of any neural net before it loads
- 🔎 Open to MLOps / Platform / Rust backend engineering roles and infrastructure consulting
| Domain | Stack |
|---|---|
| MLOps / Infra | Kubernetes · Helm · vLLM · LMCache · llm-d · KEDA · Karpenter · Prometheus · Grafana |
| Rust Backend | Tokio · Actix-web · kube-rs · candle · serde · Rayon |
| AI Compilation | MLIR · LLVM · CUDA · Triton · ONNX · custom IR design |
| ML Engineering | PyTorch · TensorFlow · Burn · MuJoCo/PPO · CNN/LSTM |
Selected from github.com/rustnew for technical depth and relevance to production AI infrastructure.
| Project | Stack | Impact |
|---|---|---|
| NEURAX | Compiler design · MLIR/LLVM concepts | Analytical compiler that predicts FLOPs, VRAM, latency & cost of a neural net before it ever runs |
| Lift | Rust · Custom IR | Next-gen intermediate representation bridging high-level ML frameworks and heterogeneous hardware (GPU, QPU) |
| Witch-Bridge (Rust ⇄ C++) | Rust · C++ · GGUF | Hybrid algorithmic trading engine with local AI inference, tuned for deterministic sub-100µs tick-to-trade latency |
| Rust_network | Rust · ndarray | Neural network built from scratch — forward/backward pass, autodiff — no ML framework dependency |
| Malaria_model_2 | Rust · Burn · CNN | Automated malaria detection from blood smear images via a CNN, fully implemented in Rust with Burn |
Building NEURAX, a static analytical compiler for neural network architectures — predicting compute cost, memory footprint, and latency before a model ever loads, to help teams plan AI infrastructure spend before committing hardware.
Active R&D: AI compiler design (NEURAX) · cross-language AI inference bridges (Rust/C++) · low-level neural network implementations in Rust.
Open to Rust / MLOps / AI infrastructure roles — let's talk.