Bogdan Truta

About

AI Engineer at ERNI and co-founder of AlphaProve, based in Cluj-Napoca. I build production AI systems, quantitative infrastructure, and autonomous-agent tooling. I took 1st place (Application Development) at PoliHack 2025 and 2nd place (AI App Development) at PoliHack 2026.

Projects

• AlphaProve: a deployed multi-tenant quantitative backtesting SaaS I co-founded. I designed the AI loop that turns plain-English strategy descriptions into backtest-ready code, the engine that simulates an exchange at tick precision with L2 order-book fills, and the self-repairing market-data store behind it.
• eGata: an AI agent that walks Romanian citizens through municipal procedures over voice, text, and telephone. Every state transition lands in a tamper-evident hash-chain audit ledger, and which tools the agent may call is decided in code from the current state. Built at Cluj Hackathon 2026 (landing page).
• seeks: a harness that runs Claude Code in long task loops. Verification gates run outside the model's control and a separate cheat-detector watches for reward hacking. Node.js with no dependencies.
• GOSHA Jobs: a deployed job-matching platform that ranks openings against a candidate's CV with sentence-transformer embeddings and Rocchio relevance feedback (source).
• FTMO Trading Calendar: a live service that syncs FTMO maintenance windows to Google Calendar. Events are extracted by several LLMs that must agree, and scheduling runs on an RFC 5545 implementation written from scratch (source).
• LearnLoop: a prompting coach that scores prompts across Claude and Copilot. Hono/PostgreSQL API, custom MCP server, Chrome and VS Code extensions, Next.js dashboard. 2nd place (AI) at PoliHack 2026.
• HistoricalCryptoDataDB: a market-data warehouse on TimescaleDB with automated gap repair, an escalating restart-ladder watchdog, and a written disaster-recovery runbook.
• TradingStats: a quantitative research framework. Hypotheses are registered before evaluation, look-ahead bias and data leakage are detected automatically, and negative results are recorded alongside positive ones.
• CS2 Weekly Item Journal: a computer-vision pipeline that reads Counter-Strike 2 weekly item drops from screenshots with a custom-trained YOLO model and OCR, then attaches live market prices.

Work experience is on the Experience page. Download my CV (PDF), or find me on GitHub and LinkedIn.