{"profile":{"name":"Eli Benbaruk","firstName":"Eli","lastName":"Benbaruk","role":"SpaceXSI Build Ambassador · Forward Deployed Engineer","headline":"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.","location":"Paris, France","timezone":"GMT+1","email":"elibenbaruk@gmail.com","status":"Open to work — internship / apprenticeship (Paris)","languages":["French — native","English — C1","Italian — B2"],"oneLiner":"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.","links":{"github":"https://github.com/ebenbaruk","linkedin":"https://www.linkedin.com/in/eli-benbaruk","email":"mailto:elibenbaruk@gmail.com","substack":"https://substack.com/@elibenbaruk"},"spotlight":{"title":"SpaceXSI Community Build Ambassador","org":"SpaceX Super Intelligence Community × Cursor","place":"Paris","blurb":"I lead the Paris builder community of SpaceX Super Intelligence (SpaceXSI) and Cursor: hackathons, meetups and hands-on build sessions for people shipping real products with AI."}},"projects":[{"slug":"hecklr","name":"Hecklr","year":"2026","stack":["Python","TypeScript","Pipecat / LiveKit / Twilio","DuckDB"],"tagline":"The crash-test lab for AI agents: simulated customers over voice, chat and email, with statistical CI gating.","problem":"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.","approach":"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.","role":"Sole author — architecture, statistics, voice stack."},{"slug":"earshot","name":"Earshot","year":"2026","stack":["TypeScript","Next.js","AssemblyAI","Gemini"],"tagline":"Voice supervision for autonomous agents: say \"stop, a bit to the left\" and the correction becomes a learned rule.","problem":"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.","approach":"\"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).","role":"Solo build."},{"slug":"badge","name":"Badge","award":"🥉 3rd place, Ledger OP3N 2026","year":"2026","stack":["TypeScript","Intel TDX","Ledger DMK","MCP"],"tagline":"Turns each employee's Ledger into their company badge for AI agents.","problem":"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.","approach":"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.","role":"Lead developer (with Alexandre Lemiere)."},{"slug":"heureka","name":"Heureka","year":"2026","stack":["Python","Pydantic","NVIDIA Nemotron","multi-agent"],"tagline":"An AI co-scientist: 7 agents that generate, refute and rank hypotheses.","problem":"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?","approach":"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.","role":"Sole author — architecture, agents, evals."},{"slug":"fendforitself","name":"FendForItself","award":"🏆 Agentic Economy on Arc 2026","year":"2026","stack":["Next.js","Gemini","x402","Arc"],"tagline":"Autonomous AI-run companies spun up in ~30 seconds.","problem":"Launching a micro-business takes dozens of manual steps. What if agents could own and operate a business end-to-end?","approach":"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.","role":"Solo build — agents, on-chain integration, frontend."},{"slug":"hypervest","name":"HyperVest","award":"🏆 Hack'inDauphine 2026 — Tokenization track","year":"2026","stack":["Solidity","HyperEVM"],"tagline":"On-chain equity vesting with Soulbound Tokens.","problem":"Equity vesting stays opaque, off-chain and hard to verify.","approach":"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.","role":"Smart contracts + frontend (with Ariles Hireche)."},{"slug":"feedforward","name":"Feedforward","year":"2026","stack":["Next.js","Muse Spark","SAM 3.1","zod"],"tagline":"A feed of work your agents already did: approve, edit or dismiss instead of prompting.","problem":"Chat makes you do the thinking: you have to know what to ask. Most useful agent work should arrive ready to approve.","approach":"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.","role":"Solo build."},{"slug":"tokengo","name":"TokenGo","year":"2026","stack":["TypeScript","Rust","NEAR","MapLibre"],"tagline":"Walk Paris. Catch AI. Spend it for real: a location game where the loot is AI inference credits.","problem":"Crypto games bolt tokens onto gameplay nobody wants. What if the reward were something players already value: compute from real models?","approach":"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).","role":"Solo build, directing AI coding agents."},{"slug":"pact","name":"PACT","year":"2026","stack":["FastAPI","React","Ed25519"],"tagline":"Identity & reputation for autonomous agents.","problem":"Agents that transact need to prove who they are and decide who to trust, with no human in the loop.","approach":"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.","role":"Protocol design + backend + interface."},{"slug":"onchain-lie-detector","name":"onchain-lie-detector","year":"2026","stack":["Python","graphs"],"tagline":"Automated crypto due diligence via fund-flow graphs.","problem":"Evaluating an on-chain protocol is slow, manual and easy to fake (inflated TVL, Sybils).","approach":"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.","role":"Design + implementation."},{"slug":"zkrust","name":"zkrust","year":"2026","stack":["Rust"],"tagline":"A Groth16 zk-SNARK built from scratch, zero crypto deps.","problem":"Truly understand zero-knowledge proofs — not just call a library.","approach":"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).","role":"Sole author — maths, implementation, tests."},{"slug":"liquidvest","name":"LiquidVest","year":"2026","stack":["Anchor","Solana","Next.js"],"tagline":"Tradeable token vesting on Solana.","problem":"Vesting tokens are locked and illiquid until the cliff ends.","approach":"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).","role":"On-chain program + indexer + frontend."},{"slug":"truth-stamped","name":"truth-stamped","year":"2025","stack":["TypeScript","Solidity","Base"],"tagline":"Cryptographic anti-deepfake timestamping.","problem":"Prove a piece of media existed at time T, in the age of AI deepfakes.","approach":"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.","role":"Design + implementation."}],"experience":[{"org":"SpaceX Super Intelligence Community × Cursor","title":"Community Build Ambassador (SpaceXSI)","context":"Paris","period":"Current","summary":"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."},{"org":"TVA Engineering","title":"Forward Deployed Engineer (promoted from Applied AI Engineer)","context":"Paris · on site","period":"Jun — Sep 2026","summary":"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."},{"org":"Euretudes","title":"AI Engineer — Intern","context":"Paris","period":"Jun — Sep 2025","summary":"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."},{"org":"Freelance","title":"Software Developer","context":"Remote","period":"2019 — now","summary":"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."}],"education":[{"org":"ESILV — École Sup. d'Ingénieurs Léonard de Vinci","title":"Engineering degree — Computer Science","context":"Paris","period":"2024 — 2028","summary":"Computer science engineering degree. Fintech major (blockchain, crypto, finance, economics, software development, machine learning) and Startup track. Clubs: Kryptosphere (blockchain), Entrepreneurs Club."},{"org":"Prépa Emc2 Hadamard","title":"Preparatory classes (CPGE) — MPSI/MP, CS option","context":"Paris","period":"2023 — 2024","summary":"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."}],"community":[{"org":"SpaceX Super Intelligence Community (SpaceXSI)","title":"Community Build Ambassador, Paris","context":"Paris","period":"Current","summary":"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."},{"org":"DeVinci Blockchain (ex-Kryptosphere DeVinci)","title":"Member","context":"Paris","period":"Sep 2025 — now","summary":"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)."},{"org":"Entrepreneurs Club — ESILV","title":"Member","context":"Paris","period":"2024 — now","summary":"Member of the school's entrepreneurship club: projects, events and mutual help around startup creation."}],"skills":{"bars":[{"name":"Python","level":92},{"name":"TypeScript / JS","level":90},{"name":"AI / LLM agents","level":93},{"name":"Agent evals & voice","level":86},{"name":"Blockchain / on-chain","level":85},{"name":"Rust","level":82},{"name":"Solidity","level":78}],"tags":["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"],"extra":"Postgres · SQLite · Linux · SQL · Pytest · Proptest / Bankrun · self-hosted LLMs (Qwen, Gemma)","stats":[{"label":"Projects shipped","value":"35+"},{"label":"Hackathons won","value":"4"},{"label":"Public repos","value":"36"}]}}