Head of Applied AI & Verifiable Intelligence
Building at the intersection of world models, AI safety, and verifiable computation.
- 15+ years shipping production software in payments, banking, cryptography, blockchain, and now AI.
- Current focus: AI safety infrastructure, world models, agent systems, and verifiable computation.
- Current role: Head of Applied AI & Verifiable Intelligence at StarkWare.
- Previously: Ethereum core developer, co-author of EIP-1559.
- Grew Starknet ecosystem to thousands of developers.
- Started and spearheaded Kakarot and Madara from zero. Both now run with independent teams and communities.
The question I keep coming back to is simple:
How do you verify what an autonomous system actually did?
Deployment is moving faster than the verification layer. That is the gap I work on.
| Project | What it is |
|---|---|
| claude-md-compiler | Compiles CLAUDE.md into a versioned policy lockfile and enforces it against diffs, hooks, and CI. |
| awesome-ai-safety | Curated map of AI safety tools and resources: alignment, interpretability, red teaming, formal verification, zkML, governance. |
| eu-ai-act-toolkit | Open-source toolkit for EU AI Act compliance. |
| llm-provable-computer | Exploring verifiable inference with STARKs. |
I implement frontier ML papers in Rust. If you can build it from scratch, you understand it.
| Project | What it is |
|---|---|
| latent-inspector | Compare DINOv2, I-JEPA, V-JEPA 2, and EUPE representation geometry on the same image. Rust + ONNX. |
| jepa-rs | Rust implementation of JEPA primitives: I-JEPA, V-JEPA, C-JEPA, VICReg, EMA. |
| gpc_rs | Generative robot policies in Rust: diffusion policy + world model + evaluator. |
| mosaicmem | Geometry-aware spatial memory for camera-controlled video generation. |
| attnres | Attention residual stream experiments inspired by Kimi / MoonshotAI. |
| turboquant | Rust implementation of Google's TurboQuant for KV-cache quantization. |
| jepa-notebooks | Interactive notebooks for JEPA architectures. |
| Project | What it is |
|---|---|
| parler | Multilingual voice intelligence built on Mistral Voxtral, focused on structured decision logs from French/English meetings. |
| Project | What it is |
|---|---|
| Kakarot | EVM interpreter written in Cairo. Ethereum compatibility on Starknet via ZK proofs. |
| Madara | Starknet sequencer for sovereign appchains. |
| Raito | Bitcoin ZK client in Cairo. Verifies Bitcoin consensus inside a STARK proof. |
| Askeladd | Verifiable computation for Nostr Data Vending Machines via STARKs. |
| Cashu ZK Engine | Blind Diffie-Hellman key exchange in Cairo for Cashu ecash. |
| Project | What it is |
|---|---|
| bitcoin-mcp | Bitcoin and Lightning MCP server. |
| nostringer-rs | Ring signatures for Nostr, in Rust. |
| nostr-mcp | Nostr MCP server. |
| bitcoin-honeybadger | Bitcoin Honeybadger. |
| Title | What it is |
|---|---|
| The Half-Life of Trust | Why verifiable AI needs post-quantum foundations. |
| Math Is Humanity's Last Bastion Against Skynet | Why ZK proofs are the foundation for AI safety at scale. |
| Can LLMs Be Provable Computers? | Verifiable AI inference via STARKs. |
| Before Fighting Banks, Let's Understand How They Actually Work | A cypherpunk's guide to the financial system. |
| Time to Take the Nostr Pill | Why Nostr matters for freedom of speech. |
| Nostr DVMs Meet Verifiable Computation | STARKs for trustless Nostr services. |
| Cashu Meets STARKs | Zero-knowledge proofs for the Cashu protocol. |
Hellhound — applied cryptography / blind computation (2018)
I co-founded Hellhound inside ConsenSys R&D: a decentralized blind-computation platform for running programs over homomorphically encrypted inputs without exposing the data to the network.
I built the HHVM register-based bytecode VM, the Paillier homomorphic encryption pipeline, the Kubernetes/GKE infrastructure, the Ethereum smart contracts for on-chain computation proofs, and the consensus logic for detecting malicious nodes. I was also first author of the Red Paper.
We shipped a live demo at DevCon4 Prague.
The thread across all of this is simple:
Close the gap between what systems claim and what can actually be verified.
Math scales. Goodwill doesn't.
