Forum Intelligence: Project Brief & Initial Rollout 1. Executive Summary & Objective Forum Intelligence is a beginning as a localized data retrieval, processing, and archiving system designed to scrape public municipal records and state legislative data for public oversight. The immediate objective is to build a functional, highly resilient prototype focused on the Tri-Cities region (Burbank, Glendale, and Pasadena, California). The system will autonomously ingest messy, unstructured municipal data (City Council meeting minutes, agendas, public notices, and legislative PDF text, recorded mp4), clean it, and make it fully searchable and queryable via a localized AI agentic framework. 2. Phase 1 Scope: The Tri-Cities Rollout Th engineer will be responsible for building two primary pillars: A. Resilient Scraper Bots • Target Ingestion: Monitor and pull data from Burbank, Glendale, and Pasadena municipal portals and California legislative feeds. • Data Types: Brittle HTML sites, heavily nested tables, public notices, legislative drafts, and massive unstructured PDF archives. • Requirements: The scraping architecture must be exceptionally robust, utilizing intelligent error handling, retry semantics, and pagination tracking to handle frequent municipal website layout changes without breaking the pipeline. B. Ingestion & Vector Pipeline • Parsing: Extracting clean text from poorly formatted documents and scanned PDFs. • Local RAG (Retrieval-Augmented Generation): Chunking and embedding the data locally into a vector database (e.g., pgvector, Chroma, or Milvus) to enable semantically accurate entity linking and contextual search. 3. Targeted Hardware Stack To ensure maximum data security, strict public oversight integrity, and predictable operational costs, Forum Intelligence is skipping commercial cloud APIs in favor of an on-premise, localized NVIDIA enterprise deployment. The production roadmap aligns precisely with the new computing patterns detailed in NVIDIA’s latest hardware roadmap: • Inference & Token Generation: Running local open-weight frontier models (e.g., Neotron 3 Ultra or Claude/Llama equivalents) optimized for reasoning and long-context tool use. • Compute & Orchestration: The backend infrastructure is architected around NVIDIA’s dedicated agentic architecture, utilizing high-instructions-per-clock (IPC) Vera CPUs paired with Vera Rubin GPUs. • Memory & Storage Processing: Utilizing NVIDIA’s unified memory fabric and data processing units (DPUs) for ultra-low latency context management, KV caching, and fast vector database retrieval. 4. Immediate Milestones for the Engineer 1. Architecture Design: Map out the database schema and local inference ingestion loop. 2. Tri-Cities Scraper Deployment: Write and deploy the initial automated bots for Burbank, Glendale, and Pasadena. 3. Local MVP Pipeline: Demonstrate a local RAG pipeline where a user can query the Tri-Cities scraped records and receive grounded answers with exact source attributions. The above was AI generated from months long conversations with Gemini. The goal is to prove the concept then roll out to LA County, state of CA, and then the country.

We are a small AI consulting practice that helps financial services firms put AI to work inside their business. Our clients are owner-led firms like accountants, business appraisers, financial advisors, and insurance agents. We do not sell one-off scripts or disposable projects. We build practical AI systems that take real work off these firms' plates, delivered through ongoing monthly work. Demand is growing and the bottleneck is delivery. We are looking for one delivery partner to own that side of the work with us. How it works: we handle marketing, sales, and the paid advisory session that starts each client. Once a client moves to ongoing work, you take the lead on delivery. You build the systems against the priorities we set each month, and you run the weekly client meeting as their main point of contact. We stay in for support, to translate the client's business context, and to own the relationship at the top, but week to week the client works with you. What you would own: -Building AI and agentic systems for clients -Running the weekly client meeting and being the client's day-to-day contact -Taking each engagement from kickoff through delivery on the month's agreed hours, to a standard we can stand behind Compensation is $100/hour for your hours, which include both build time and client meetings. Straightforward and paid against tracked hours. As our client book grows, so do the hours available. Who we are looking for: -Genuinely fluent building real systems with modern AI tools. -Not just familiar with them. You should be comfortable architecting and shipping working systems for non-technical business owners. -Client-ready. You can run a working session, explain technical things plainly to a non-technical owner, and hold a client relationship week to week. -Native or fluent English. You are in front of clients every week, so clear, natural communication is non-negotiable. -Strong general technical judgment. The specific stack matters less than the ability to find the right solution and build it. -Reliable. We scope the work and stand behind it, so we need to count on what you deliver and how you handle the client. Who this is not for: anyone looking to own sales or pricing, anyone who only wants to build quietly and never talk to a client, and anyone new to this work hoping to learn on the job. To apply, tell us briefly: the most relevant AI system you have built and what it did for the business, how comfortable you are leading client calls, and how you approach building these systems. Start your reply with the word "Agentic" so we know you read this in full. Applications without it will not be reviewed. We will move quickly with the right person.