Eli Benbaruk

SpaceXSI Build Ambassador · Forward Deployed Engineer

SpaceXSI Community Build Ambassador in Paris. Forward Deployed Engineer and engineering student @ESILV: I ship production AI agents for real companies, and build multi-agent systems and on-chain protocols.

Shipping production software since I was 14. As a Forward Deployed Engineer I put AI agents in production across 5 companies (one resolves 68% of 4,000 monthly support requests on its own). 4× hackathon winner, 3rd at Ledger OP3N, 4th at the RAISE Summit hackathon.

Localisation : Paris, France

Statut : Open to work — internship / apprenticeship (Paris)

Langues : French — native, English — C1, Italian — B2

Expérience

Community Build Ambassador (SpaceXSI) — SpaceX Super Intelligence Community × Cursor

Paris · Current

Selected as the SpaceXSI Community Build Ambassador for Paris. I grow a community of ambitious builders, hackers, founders and AI enthusiasts: hackathons, meetups and hands-on building sessions to turn ideas into real products, with SpaceX Super Intelligence and Cursor.

Forward Deployed Engineer (promoted from Applied AI Engineer) — TVA Engineering

Paris · on site · Jun — Sep 2026

Promoted after two months from Applied AI Engineer to Forward Deployed Engineer, working directly with clients to deploy production AI across 5 companies. Shipped a multimodal support agent (voice, chat, email) for a maintenance group that autonomously resolves 68% of 4,000 monthly requests, with sub-800 ms voice latency; built an evaluation pipeline replaying 500 real conversations to gate every prompt or model change; turned it into a reusable deployment framework that cut rollouts from 6 weeks to 5 days. Before that, as Applied AI Engineer at the 70-person firm: hybrid AI infrastructure (Claude API + self-hosted Qwen/Gemma with model routing and guardrails), custom Python MCP servers into the ERP, a new internal ERP, AI sales agents, CRM and Microsoft 365 automations. Dozens of hours saved per week, ~10 major clients won.

AI Engineer — Intern — Euretudes

Paris · Jun — Sep 2025

Helped the company adopt AI and become agentic. Small custom agents per team (recruiting side: sourcing, CV screening, profile formatting, follow-ups, scheduling) and drove day-to-day adoption. Went from near-zero AI to agents used daily by 30+ recruiters; ~50 employees touched by the tooling. Training and explaining for non-technical colleagues.

Software Developer — Freelance

Remote · 2019 — now

35+ projects shipped end-to-end for SMBs (e-commerce, consulting, services), started at 14. React/TypeScript frontends, custom backends, full lifecycle: scoping → build → launch → support. Google Ads campaigns at ~2× ROAS on average. What it taught me: a product's real value lives in the messy parts of a business.

Formation

Engineering degree — Computer Science — ESILV — École Sup. d'Ingénieurs Léonard de Vinci

Paris · 2024 — 2028

Computer science engineering degree. Fintech major (blockchain, crypto, finance, economics, software development, machine learning) and Startup track. Clubs: Kryptosphere (blockchain), Entrepreneurs Club.

Preparatory classes (CPGE) — MPSI/MP, CS option — Prépa Emc2 Hadamard

Paris · 2023 — 2024

Selective post-bac track preparing for the competitive entrance exams to France's top engineering schools. Maths, physics, engineering science, computer science. Ranked top 20 in France for MP.

Communauté & leadership

Community Build Ambassador, Paris — SpaceX Super Intelligence Community (SpaceXSI)

Paris · Current

Paris lead for the SpaceXSI × Cursor builder community: hackathons, meetups and build sessions. If you're building something with AI in Paris, come build with us.

Member — DeVinci Blockchain (ex-Kryptosphere DeVinci)

Paris · Sep 2025 — now

The school's blockchain association (Kryptosphere until Feb 2026). I help organize The Great Hack, on track to be Europe's largest student blockchain hackathon (partners: Sui, XRPL, RedStone, iExec, Hyperliquid, MegaETH, Arc, Circle, Hedera, Arbitrum), and compete under its colours (Ledger OP3N, RAISE Summit).

Member — Entrepreneurs Club — ESILV

Paris · 2024 — now

Member of the school's entrepreneurship club: projects, events and mutual help around startup creation.

Projets (études de cas)

Hecklr (2026)

The crash-test lab for AI agents: simulated customers over voice, chat and email, with statistical CI gating.

Problème : Teams ship customer-facing agents on vibes: a prompt tweak can silently break 1 call in 4, and nobody notices until customers do. Agent quality needs the same rigour as code.

Approche : Each scenario × trial resets a sandboxed world (mock backend over MCP/HTTP) and sends a persona-driven simulated customer at the agent through adapters (HTTP/SSE/WS, Twilio, Pipecat, LiveKit, SMTP/IMAP), with real audio, noise, codecs, packet loss and barge-in. Graders combine deterministic checks, tool/state assertions and LLM judges calibrated with Cohen's κ; stats use Wilson and cluster-bootstrap CIs, a paired sign-flip test and Benjamini-Hochberg. Plus a miner (prod logs → scenarios), a fixer (validated prompt patches → PR) and an 8-strategy red-team pack.

Impact : The hecklr gate command comments the PR and fails the build on a real regression: demo catch −27.3 pts [−44.2, −11.2], p = 0.004. 1.8% false alarms over 2,000 A/A runs, 90.6% power for a 10-pt drop, voice timing error ≤ 18 ms, 12/12 seeded faults caught.

Rôle : Sole author — architecture, statistics, voice stack.

Stack : Python, TypeScript, Pipecat / LiveKit / Twilio, DuckDB

Earshot (2026)

Voice supervision for autonomous agents: say "stop, a bit to the left" and the correction becomes a learned rule.

Problème : Robots and agents act faster than humans can type. Operators need to interrupt and correct them by voice, and the same mistake shouldn't happen twice.

Approche : "Stop" is caught on AssemblyAI partial transcripts; the rest of the sentence becomes a skill call (grammar first, LLM fallback). Each correction is logged with 2 s of prior state, then distilled into a new policy version: LLM rules with evidence plus deterministic operator facts. Hierarchical LLM policy over a frozen skill layer, with watchdogs; demo on a simulated gantry gripper.

Impact : Halts in ~250–300 ms; operator interventions drop from 4 to 0 on the next run. 192 unit tests, live demo. Built for the AssemblyAI Voice Agent Hackathon (lablab.ai).

Rôle : Solo build.

Stack : TypeScript, Next.js, AssemblyAI, Gemini

Badge — 🥉 3rd place, Ledger OP3N 2026 (2026)

Turns each employee's Ledger into their company badge for AI agents.

Problème : Your AI agent knows too much; your colleague's knows too little. The most valuable context lives in private conversations and documents, and agents have no safe way to share it with consent.

Approche : A confidential enclave (Intel TDX on Phala, attestation verified by clients) finds the relevant notes in a colleague's memory; the owner approves each excerpt on their Ledger through clear-signed EIP-712 messages. Consent expires, anti-scraping limits stop hijacked agents, and desks behind a Chinese wall answer through Semaphore ZK proofs. Agents plug in over MCP.

Impact : 3rd of 13 student teams at Ledger OP3N ($1,000), built in one week, the only podium project that didn't move money. Open source, live demo.

Rôle : Lead developer (with Alexandre Lemiere).

Stack : TypeScript, Intel TDX, Ledger DMK, MCP

Heureka (2026)

An AI co-scientist: 7 agents that generate, refute and rank hypotheses.

Problème : Research is bottlenecked by how many hypotheses a team can generate and seriously test. How do you surface testable ideas you wouldn't have had?

Approche : 7 specialised agents in an adversarial loop: generation (expert debate) → critique → falsification (red-team) → safety → Elo tournament ranking → evolution. Claim-level verification: each hypothesis is broken into atomic claims checked against open-access literature (OpenAlex, Europe PMC, arXiv); conjunctive scoring — a single contradicted premise collapses the score.

Impact : Ranked hypotheses (lower-confidence-bound Elo) with claim graphs, novelty measured against the nearest prior work, falsification verdicts and proposed experiments. Runs on any OpenAI-compatible model (default NVIDIA Nemotron), with per-role routing, a budget-driven orchestrator and resumable runs. Ships its own eval harness: the scaffold vs. a one-shot call to the same model, judged blind.

Rôle : Sole author — architecture, agents, evals.

Stack : Python, Pydantic, NVIDIA Nemotron, multi-agent

FendForItself — 🏆 Agentic Economy on Arc 2026 (2026)

Autonomous AI-run companies spun up in ~30 seconds.

Problème : Launching a micro-business takes dozens of manual steps. What if agents could own and operate a business end-to-end?

Approche : Each generated company gets its own wallet, USDC funding and a priced API (x402-protected). Agents spawn, pay and coordinate on Arc.

Impact : Winner, Agentic Economy on Arc 2026 (Circle + Arc + Lablab.ai). Demo: 60 buyer agents settling on-chain over real-time SSE. $0.005/call at ~98% margin — viable because USDC is Arc's native gas.

Rôle : Solo build — agents, on-chain integration, frontend.

Stack : Next.js, Gemini, x402, Arc

HyperVest — 🏆 Hack'inDauphine 2026 — Tokenization track (2026)

On-chain equity vesting with Soulbound Tokens.

Problème : Equity vesting stays opaque, off-chain and hard to verify.

Approche : Vesting anchored on non-transferable Soulbound Tokens, with performance-based unlocks (MRR targets, GitHub commits, KPIs) instead of pure time.

Impact : Winner, Tokenization track at Hack'inDauphine 2026 (Kryptosphere). Solidity + OpenZeppelin v5, Foundry, deployed on HyperEVM Testnet.

Rôle : Smart contracts + frontend (with Ariles Hireche).

Stack : Solidity, HyperEVM

Feedforward (2026)

A feed of work your agents already did: approve, edit or dismiss instead of prompting.

Problème : Chat makes you do the thinking: you have to know what to ask. Most useful agent work should arrive ready to approve.

Approche : Miner → parallel Preparers → client-side Ranker → sandboxed Executor, streamed as typed NDJSON. 7 roles on Muse Spark with strict JSON schemas generated from zod, Muse Image and SAM 3.1 segmentation for photo snaps. Rule: the model writes the words, code owns the facts (metrics and calendar slots are computed). A taste memory rewrites the Miner prompt every 3 gestures; an Agent Lens shows every call live.

Impact : Built solo for the Meta Global AI Developer Hackathon 2026 (Indie track). Unit + Playwright E2E tests on 2 viewports, demo video.

Rôle : Solo build.

Stack : Next.js, Muse Spark, SAM 3.1, zod

TokenGo (2026)

Walk Paris. Catch AI. Spend it for real: a location game where the loot is AI inference credits.

Problème : Crypto games bolt tokens onto gameplay nobody wants. What if the reward were something players already value: compute from real models?

Approche : Model shards spawn around OpenStreetMap places, deterministically (HMAC over H3 cell × time window). LLM-driven shopkeepers price from their own stock, so walking between shops is arbitrage; 3v3 Model Arena battles. Items are NEP-245 tokens on a hand-written Rust contract; compiling a recipe burns shards on-chain and credits a NEAR AI Cloud key. The player never sees a wallet.

Impact : 292 unit tests, 36 E2E flows, 1,060 relays and 153 shops across Paris, difficulty tuned over 2,000 simulated battles. Live, built solo for the NEAR Hackathon (games track).

Rôle : Solo build, directing AI coding agents.

Stack : TypeScript, Rust, NEAR, MapLibre

PACT (2026)

Identity & reputation for autonomous agents.

Problème : Agents that transact need to prove who they are and decide who to trust, with no human in the loop.

Approche : Three phases: cryptographic handshake (capabilities + Ed25519-signed bonds), discovery (need/capability matching), and a Web of Trust (referrals via bonded peers).

Impact : 20+ REST endpoints, network visualization dashboard, two demos (one fully LLM-driven, one scripted). Infra brick for trustworthy agent economies.

Rôle : Protocol design + backend + interface.

Stack : FastAPI, React, Ed25519

onchain-lie-detector (2026)

Automated crypto due diligence via fund-flow graphs.

Problème : Evaluating an on-chain protocol is slow, manual and easy to fake (inflated TVL, Sybils).

Approche : Ingests 4 heterogeneous sources (Alchemy RPC, Dune, Etherscan, DefiLlama), builds a fund-flow graph, runs Louvain clustering + Johnson's cycle detection to spot circular flows and Sybil networks.

Impact : 0–98 trust score across 5 weighted dimensions. 108+ tests. Replaces hundreds of hours of manual investigation per protocol.

Rôle : Design + implementation.

Stack : Python, graphs

zkrust (2026)

A Groth16 zk-SNARK built from scratch, zero crypto deps.

Problème : Truly understand zero-knowledge proofs — not just call a library.

Approche : Full Groth16 over BN254: hand-rolled Montgomery field arithmetic (Fp/Fp2/Fp6/Fp12), optimal Ate pairing, Pippenger MSM, KZG commitments, radix-2 NTT. CLI setup → prove → verify.

Impact : ~6,500 lines of Rust, 159 tests, 6-crate workspace. ~1 ms to generate a proof, ~13.5 ms to verify (Apple Silicon).

Rôle : Sole author — maths, implementation, tests.

Stack : Rust

LiquidVest (2026)

Tradeable token vesting on Solana.

Problème : Vesting tokens are locked and illiquid until the cliff ends.

Approche : Each vesting schedule is a transferable Receipt NFT — selling the NFT sells the future token stream. Linear / cliff / step curves.

Impact : Anchor 0.30.1 program, Node.js + better-sqlite3 indexer, Next.js frontend. Property-based tests (Proptest) + 13 integration tests (Bankrun).

Rôle : On-chain program + indexer + frontend.

Stack : Anchor, Solana, Next.js

truth-stamped (2025)

Cryptographic anti-deepfake timestamping.

Problème : Prove a piece of media existed at time T, in the age of AI deepfakes.

Approche : On-chain timestamping: SHA-256 + ECDSA signatures + immutable record on Base.

Impact : Live on Base Sepolia, 12 tests, ~$0.001 per stamp. Defensive content-authentication infrastructure.

Rôle : Design + implementation.

Stack : TypeScript, Solidity, Base

Compétences

Outils & technos : Next.js, React, FastAPI, Anchor, Foundry, viem / wagmi, Claude Code, Anthropic API, Gemini API, LangChain, MCP, Solana, EVM, zk-SNARKs, x402, Ed25519, LLM evals, Voice agents, OpenAI Realtime, Pipecat / LiveKit, AssemblyAI, Cursor, Intel TDX, NEAR

Aussi : Postgres · SQLite · Linux · SQL · Pytest · Proptest / Bankrun · self-hosted LLMs (Qwen, Gemma)

Liens