Jordi Albarracin i Puig@Albarracin
1
Events attended
1
Submissions made
Spain
1 year of experience
About me
Technical Project Manager & AI Product Builder. Experienced in deploying end-to-end AI ecosystems, self-hosted LLM infrastructure (ROCm / vLLM), and scalable SaaS applications. Passionate about autonomous agents, multimodal AI architectures, and building production-ready MVPs. Currently focused on the AMD AI League, competitive hackathons, and high-performance local AI deployment. Always building.
🤓 Latest Submissions
.png&w=828&q=75)
ROMA: Autonomous Exact Web Intelligence Agent
ROMA is a production-grade, deterministic autonomous web intelligence agent engineered specifically for the AMD AI League Match 4 (Intelligent Web Information Retrieval) challenge. Powered by the AMD ROCm ecosystem and open-source models, the agent navigates live web environments, retrieves specific normalized target values, and guarantees exact source URL attribution. Key Architecture: 1. Sub-Second Latency: Average query response time of 0.53s on benchmark evaluations, well within the 30-second budget. 2. Dual-Engine Architecture: Resident background daemon in VRAM communicating with an ultra-lightweight CLI client (/app/app.py) via local RPC. 3. Zero-API Key Dependency: Keyless retrieval aggregating DuckDuckGo, Wikipedia REST API, and direct registry endpoints (PyPI, npm). 4. Strict Cite-or-Refuse Verifier: Enforces literal substring containment against source text. Fictional or ungrounded queries cleanly return empty answers and empty citations, eliminating hallucination penalties. 5. AMD ROCm Certified: Packaged directly from the official rocm/pytorch base image with dependency isolation for AMD Instinct MI300X accelerators.
1 Dec 2026
