Yassir Sobhi@yassirsobhi1944451
2
Events attended
1
Submissions made
Italy
2+ years of experience
About me
Backend Python Developer with experience working on real-world projects within teams and structured organizations, focusing on distributed systems, multi-service architectures, and cloud infrastructure. I develop asynchronous REST APIs using FastAPI and Django, design relational and NoSQL databases, work with SQLAlchemy and SQLModel, manage database migrations with Alembic, and implement authentication and authorization systems using OAuth2, JWT, and RBAC. I have worked with multiple databases in parallel, including PostgreSQL, MariaDB, and MS SQL Server, as well as asynchronous messaging systems using MQTT. I containerize applications with Docker and Docker Compose, deploy serverless applications on AWS using Lambda and Fargate, and work with complete cloud architectures. I also have experience with structured Git workflows and CI/CD pipelines. I build advanced web scrapers and automate browsers using Playwright, including working with residential proxies and bypassing anti-bot systems at enterprise scale. On the frontend side, I have worked with Svelte, React, and TypeScript. I write automated tests at all levels — unit, integration, and end-to-end — and follow code quality and engineering standards within team environments. More recently, I have been focusing on AI development, working on personal projects involving multi-agent systems and Retrieval-Augmented Generation (RAG).
🤝 Top Collaborators
.png&w=640&q=75)
🤓 Latest Submissions
The Silent Council
A small business signs contracts it cannot afford to have a lawyer read. The Silent Council reads them: three AI experts that never speak to each other. A contract arrives by email. On an AMD Instinct MI300X a legal, a finance and a risk expert each read their part, and instead of writing to each other they pass on their memory: the KV cache of what they read. No summaries, nothing lost in translation. A rapporteur writes the verdict (sign, negotiate or do not sign) with exact quotes, and every disagreement goes to a person, who decides. Measured, not claimed. In a pre-registered evaluation on the CUAD contract benchmark, the same council ran in telepathy and in text: telepathy kept the quality with 75% fewer tokens, almost 3x faster (54 s instead of 144 s). What shared memory makes possible: - Long contracts: a router sends them to Gemma 4 31B, whose long context holds the whole contract, and short ones to Qwen3-14B. 77.4 F1, against 68.6 for Qwen alone. - Pages, not just text: using Gemma 4 31B's multimodality, a visual expert looks at the pages with signatures, stamps and scans, and its long context keeps those pages next to the clauses. The experts get them as KV cache, never as text. A missing signature lands in the email instead of being buried in a PDF. - Questions the next day: the PDF is never stored, but the memory of the review stays on the GPU, pages included. Asked about details nobody had planned for, like the seal's shape or a mark next to an empty signature field, the council answered 4 of 4 right in telepathy and 1 of 4 in text, where only a written summary survives. - A council that learns: every choice the company's people make becomes a precedent at the head of the next reviews. Evolus receives the email, calls the council on the MI300X and sends the person the verdict.
18 Oct 2026
