We are building an early-stage real estate data platform that collects, cleans, enriches, and serves public-record and legal-notice data for real estate investors and professionals. This is not a greenfield build. We already have an existing backend repo with API routes, database models, migrations, scraping workers, tests, Docker configuration, and cloud deployment pieces. We need a strong backend engineer who can step into the existing system, understand what is working, identify what is risky, and help us get the backend stable enough for launch. The right person is practical, scrappy, and comfortable working in a startup environment where the goal is not perfection. The goal is to find the highest-leverage path to a reliable product. The platform involves: -Public-record and legal-notice data -Property data enrichment -API endpoints used by a frontend application -Data quality, reliability, and launch-readiness Current Backend Stack The backend is built primarily in Python and includes: -FastAPI -SQLAlchemy and Alembic -Postgres / Google Cloud SQL -MongoDB helper/caching layer -Scraping and ETL pipeline for public-record and legal-notice data -Playwright/Patchright-based scraping -reCAPTCHA-aware scraping workflows -LLM-based data extraction / AI-assisted parsing of unstructured notice data -Pydantic models -Google Cloud integrations: Cloud Run, Cloud Scheduler, Pub/Sub, Secret Manager, Cloud Storage, Artifact Registry -Docker -Pulumi infrastructure-as-code -GitHub Actions CI/CD -pytest, Ruff, uv You do not need to be world-class in every tool listed above, but you should be strong enough in Python backend systems, scraping/data pipelines, and cloud deployment to quickly understand the architecture and make sound technical decisions. What We Need Help With We need someone who can: -Review and understand the current backend architecture -Stabilize and improve the scraping / ETL pipeline for public-record and legal-notice data -Make sure public-record and legal-notice data is collected, parsed, stored, and served correctly -Improve backend APIs used by the frontend -Improve data quality checks for incomplete, missing, or inconsistent property records -Build and maintain property enrichment workflows using external data sources -Help design database models for richer property history and event tracking -Improve LLM-assisted parsing of unstructured legal notice data where appropriate -Debug deployment, CI/CD, Cloud Run, and infrastructure issues -Improve logging, error handling, monitoring, and observability -Strengthen test coverage where it matters -Help document the backend so future developers can contribute -Coordinate with our frontend developer to support product launch -Help prioritize backend work based on launch impact, data reliability, and technical risk Who This Is For You are likely a strong fit if you: -Like working inside existing codebases -Can diagnose messy systems without needing everything rewritten -Think in practical tradeoffs, not just ideal architecture -Are comfortable with incomplete documentation -Have experience with scraping/ETL workflows and unstructured data extraction -Can explain technical risks clearly to a non-technical founder -Prefer shipping useful improvements over debating perfect abstractions -Are willing to own outcomes, not just complete assigned tickets Who This Is Not For This is probably not the right fit if you: -Only want clean, fully documented codebases -Prefer to rebuild from scratch by default -Need enterprise-level process before making progress -Are an agency sending rotating developers -Only want tightly defined tickets with no ambiguity -Are uncomfortable with scraping, data quality, or production debugging Hiring Process We want to keep the hiring process practical and focused on real work. 1. Initial Screening We will review your proposal, background, and screening question responses. 2. Real-World Technical Scenario Strong candidates may be asked to respond to a specific backend issue from our current roadmap. We are looking for how you think, what tradeoffs you notice, and how clearly you communicate. 3. Paid Finalist Review A small number of finalists may be invited to complete a paid review of the existing backend codebase before any larger implementation work begins. Budget / Working Style We are an early-stage company and are looking for a practical, startup-minded developer. This is a paid contract role, but we are not looking for enterprise-agency rates. We value clear communication, efficient execution, and someone who can help us prioritize the highest-leverage backend work first. The first paid technical review may be structured as a fixed-price milestone. Continued implementation work may be hourly or milestone-based depending on fit. Long-Term Opportunity Our goal is to find someone who can become a long-term backend partner for the product, not just complete isolated tickets. For the right person, there may be an opportunity to grow into a technical lead / backend ownership role with additional upside tied to company performance. We are looking for someone who wants to help take a real product to market, but the initial engagement will be paid, scoped clearly, and focused on proving mutual fit.

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 looking for a strong software engineer who can build practical automation systems using AI, APIs, and modern development tools. This role is for someone who can take messy business workflows, understand the goal, and build working systems that save time, reduce manual work, and improve execution. You should be comfortable building automations, integrating tools, working with APIs, writing clean code, and using AI tools like OpenAI, Claude, or similar models to create useful business applications. What You’ll Work On You will help build and improve systems such as: AI-powered research and data extraction workflows CRM and sales process automations Email, spreadsheet, and database automations Internal tools and dashboards API integrations between business software Web scraping and data enrichment workflows when appropriate AI agents or assistants that help with repetitive business tasks Automation around deal screening, reporting, lead research, and document creation Ideal Candidate We are looking for someone who is practical, fast, and can figure things out without needing step-by-step instructions. You should have experience with: Python and/or JavaScript APIs and webhooks OpenAI, Claude, or other LLM APIs Automation tools like Zapier, Make, n8n, Airtable, Google Sheets, HubSpot, Salesforce, or similar Databases such as PostgreSQL, Supabase, Firebase, or similar Basic front-end or internal tool development Web scraping, data cleaning, and structured data workflows GitHub and clean documentation What Matters Most We do not need someone who only talks about AI. We need someone who can actually build. The right person should be able to: Understand a business process quickly Recommend the simplest technical solution Build fast prototypes Turn prototypes into reliable workflows Communicate clearly Document what was built Improve systems over time Nice to Have Experience with any of the following is a plus: Private equity, M&A, finance, or investment workflows Deal sourcing or lead generation systems CRM automation Data enrichment tools AI research agents Browser automation Cloudflare, AWS, Google Cloud, or similar infrastructure Engagement This will start as a part-time project-based role, with the potential to become ongoing if the work is strong. Estimated workload: 5 to 15 hours per week to start. To Apply Please include: Examples of automations or AI tools you have built The tech stack you usually work with A brief explanation of how you would approach automating a messy manual workflow Your hourly rate Your availability Please do not send a generic application. If your response looks copied and pasted, it will be ignored.

Job Title: Automation & AI Developer — Solar Interconnection Workflow System Project Overview: We are a small but fast-growing startup in the Texas solar/energy sector looking for an experienced automation developer to build a multi-portal workflow automation system. This system will eliminate manual data entry, automate government and utility portal submissions, and use AI to analyze and validate photos. This is a paid project with strong potential for ongoing Phase 2 work as the platform grows. What You Will Build: 1. Multi-Portal Web Automation Using Playwright or equivalent browser automation tools you will automate login, navigation, form filling, file uploads, button clicks, page load waiting, and data extraction across multiple web portals including a utility interconnection portal, a project submission portal with existing API access, and a city permit portal. The utility portal specifically requires multi-page form completion, calculate button interactions with 5-15 second page refresh waits, file downloads, and triggering DocuSign email delivery to customers. 2. API Integration One portal has existing API access. You will build direct API calls for data submission and photo uploads to that portal rather than browser automation. 3. AI Photo Analysis — Two Functions First, field photos of electrical equipment must be analyzed using AI vision (Claude, GPT-4V or equivalent) to automatically extract technical data and pre-fill intake forms — eliminating manual data entry. Second, homeowner-submitted photos received via SMS must be automatically analyzed for completeness and quality. If a photo is blurry, incorrect, incomplete, or unusable the system must prompt the homeowner to retake and resubmit before the photo enters the workflow. 4. Automated Customer Notifications Immediately following the utility portal DocuSign email trigger the system must automatically send the homeowner an SMS message instructing them to check their email and sign the DocuSign document. 5. Status Monitoring & Polling The system must automatically check utility portal application statuses on a scheduled basis over a multi-day period and alert the team when a status changes or receives approval. If a DocuSign link expires without being signed the system must reinitiate the email and send the homeowner a new SMS notification automatically. 6. Mobile Application Integration This automation system will need to integrate with a proprietary mobile application currently in development. All work must be built with clean integration in mind from day one — API-ready, well-documented code is required throughout. This system will also need to support incoming and outgoing webhooks with an existing CRM for specific workflow triggers. Thorough documentation is required as a deliverable, not an afterthought. The developer must treat all systems, workflows, and code as strictly confidential. 7. Central Dashboard A simple internal dashboard to view all active jobs, their current stage in the pipeline, status updates, visual graphs or charts for easy review and identification of issues, and any items requiring human attention or intervention. Required Skills: Playwright or Puppeteer browser automation, REST API integration, AI vision API experience (Anthropic Claude or OpenAI), backend development (Python or Node.js), webhook and SMS integration (Twilio or equivalent), scheduled job and polling workflow experience, basic frontend for internal dashboard, experience building systems designed for third party app integration. Important: All code and intellectual property produced under this contract is owned exclusively by the client. A work-for-hire and IP assignment agreement must be signed prior to project commencement. An NDA is also required. Do not apply if you are unwilling to sign these agreements. To Apply: Please share examples of similar automation or RPA projects you have built, specifically any experience with government or utility portal automation, multi-step form automation, or AI vision integration. Include your proposed timeline and fixed-fee project quote.

I’m looking for a developer to help me build a platform that predicts World Cup match results and refines those predictions with real-time data. The project will involve leveraging AI algorithms, machine learning models, historical match data, player stats, and live performance metrics to create accurate match predictions. The platform will need to continuously update and vet these predictions based on new data as the tournament unfolds. If you're passionate about soccer, AI-driven solutions, and real-time systems, this could be an exciting challenge for you. The role will involve developing a scalable platform using technologies like React, Node.js, and possibly Python for data analysis and machine learning. You'll integrate real-time data through APIs to pull match stats and player performance information. AI will be central to the prediction system, with algorithms that analyze historical trends and live data to improve accuracy. You’ll also create a vetting process to ensure predictions remain sharp and reliable as the tournament progresses. The platform must be able to handle high traffic during live events while offering a seamless user experience. I’m looking for someone with experience in AI-based prediction systems, strong web development skills (React, Node.js), and familiarity with working with APIs for real-time data integration. If you have a background in machine learning, real-time data processing, and sports analytics, that would be a major plus.

I'm looking for an experienced Multi-Agent AI Engineer to review and improve an existing AI agent orchestration platform. The ideal candidate will be able to quickly understand a complex codebase, identify architectural and performance bottlenecks, and recommend practical solutions for enhancing the system. This engagement is not focused solely on implementing new features. We are seeking someone who can thoroughly analyze the current architecture, evaluate existing workflows, identify areas for improvement, and provide both strategic and technical recommendations to make the platform more scalable, reliable, and maintainable.

We're building a data-driven platform in the beauty/cosmetics space. We've already collected a very large volume of scraped product and brand data, and it's messy - inconsistent formats, duplicates, missing fields, mixed languages, and unreliable values. Your job is to turn that raw data into something clean and reliable, and to build the web application on top of it. This is not a quick gig. We're looking for someone to stay with us for roughly a year and grow with the product. What you'll be doing Building and maintaining a Next.js (App Router) front end and back end Designing and managing our Supabase setup (Postgres schema, RLS policies, auth, storage, edge functions) Cleaning, normalizing, and deduplicating large beauty datasets (this is a major part of the role) Building data pipelines to process and validate incoming scraped data Writing transformation/normalization logic (units, brand names, categories, ingredients, pricing, etc.) Setting up data-quality checks and monitoring Iterating on features with us as the product evolves You should have Strong production experience with Next.js and Supabase (please point to specific projects) Solid SQL/Postgres skills - not just ORMs Real experience cleaning and normalizing large, messy datasets (Python/pandas or similar is a plus) Comfort working with scraped data and all the inconsistencies it brings Good written English and reliable communication Ability to work independently and own your part of the product Nice to have Experience in e-commerce, catalog, or product-data projects Familiarity with data pipelines / ETL tooling Some ML/NLP experience for entity matching or text cleanup Budget We expect this to run around $4,000–$5,000 USD per month depending on experience and hours. This is a long-term commitment, so stability and quality matter more to us than the lowest rate. To apply, please include: Similar past work - links or short descriptions of Next.js + Supabase projects, and at least one data-cleaning/normalization project you've done. Your time zone and your typical available hours - we need to know there's reasonable overlap. Your expected monthly budget within the range above (or your rate if hourly). Applications that don't address all three points will not be considered. A short note on how you'd approach cleaning messy beauty product data is a big plus. We read every proposal carefully and respond quickly to strong candidates. Looking forward to working with you.

We are looking for an expert backend developer and automation engineer to extend an existing, production-grade Model Context Protocol (MCP) server and overhaul its orchestration layer. The headline correction for this project: the existing Lawfather MCP is to be retained and extended, not rebuilt. It already exposes deterministic, parameterized Playwright tools for every required county portal (District Clerk, HCSO, HCDAO) and a client database. Those backend tools are the reliable layer and are not the source of the instability this project exists to fix. The instability lives entirely in the orchestration layer — the model-driven layer that decides when and how to call the tools. The fix is to move deterministic control out of model-followed prose and into code, and to host the agent on an always-on machine with persistent memory. Core Project Principles • Extend, Don't Rebuild: Retain and extend the existing MCP; do not re-implement portal scrapers from scratch. • Code Over Prompts: Deterministic logic lives strictly in tool code, never in instructions the model must remember each session. • No Caller Loops: Batch operations must run to completion server-side. No operation may require the caller (model) to loop. • Agnostic Architecture: The system must remain model-agnostic and host-agnostic. No single provider — Anthropic, OpenAI, Z.ai/GLM, or Nous — may be a hard dependency. • Privilege First: Client data stays on owned hardware; the model is never the gatekeeper of which case a file belongs to. Existing Tool Inventory (To Be Inherited As-Is) The following tools already exist on the production MCP (containerized on a local Synology NAS) and are in daily use. Re-deriving their behavior is completely out of scope: • hcdc_get_docket: Court settings by date range + bar number (District Clerk). • hcdc_check_filings: Per case: standard defense filings present vs. missing. • hcdc_download_filings: Images-tab documents: bulk OR selective by filters; dest_subfolder; dry_run. Note: The parameterized download tools already cover most retrieval requests. "All filings," "this filing," "all subpoenas," "all resets," and "everything filed that day" are argument combinations on this tool, not separate features. • hcso_locate: Defendant custody location (facility / floor / pod) by SPN. • hcdao_grab_file: Download a single named file from the DA portal Files tab. • hcdao_download_discovery: Batch / delta discovery download from the DA portal. • hcdao_download_media_alert: Batch-download files listed in a 'New Media Available' portal email. • hcdao_case_summary: Scrape the Case Jacket quick summary / DAO narrative. • hcdao_plea_offer: Scrape current plea offer + full offer history. • hcdao_assigned_ada: Assigned ADA name / email / phone on a case. • lookup_client / list_clients: Resolve / list clients from the shared client database. Scoped Work (Paid Deliverables) 1. County Case Resolver (New Tool): Find a case from partial identifiers — any subset of (name, SPN, DOB, court, cause). Searches county systems (not just the local client DB). MUST return a ranked candidate list for the user to choose from; MUST NEVER auto-select. Wrong-defendant selection is a privilege failure, not a cosmetic bug. 2. Latest-Version Retrieval: Add scope=latest to hcdao_grab_file so 'most recent' selects the newest among supplements instead of the first match. 3. Async Transcribe Tool (Skill to Tool Promotion): Build a deterministic MCP tool using Gemini 3.1 Pro Preview for transcription, followed by a second pass that sends the transcript back with case context for cleanup (speaker mapping, defense-moment preamble). Long-running: implement as an async job (submit to job id to poll to fetch), NOT a synchronous call. 4. OCR Tool (Skill to Tool Promotion): Implement a readability check on ingest. If a document is not cleanly readable, FLAG it and ASK before sending to Gemini 3.1 Pro Preview for OCR. OCR must be gated and confirmed, never automatic. 5. Server-Side Batch Jobs: Move all chunk, loop, delta, and throttle logic OFF the caller and INTO the tool code. One call runs the batch to completion. 6. Queued HCDAO Fixes: For hcdao_download_discovery, add a portal_ids filter for targeted single-file pulls and a custom output-path / Drive-folder destination feature. Known Portal Quirks to Handle from Day One • hcdc_get_docket returns a broader date range than requested; results must be filtered to the requested window. • hcdao_download_discovery delta detection is blind to files organized into dated subfolders and must be explicitly handled. • Court DG7 does not surface through standard bar-number docket lookup and requires separate handling. • The Playwright Node.js driver subprocess can die silently while database tools respond; you must health-check the driver proactively. Orchestration, Host Layer, & Deployment Topology • Target Host: Hermes Agent (Nous Research) running as the persistent shell, providing persistent memory, the scheduler, and messaging surfaces. The MCP server will plug directly into it. • Agnostic LLM Routing: Default the agent/dispatch role to the most reliable tool-calling model (currently Claude Opus). Route bulk, non-critical generations (draft summaries, transcript cleanup) to a cheaper model (e.g., GLM-5.2). No provider may be hard-wired. Per-tool pins are allowed strictly for transcription/OCR tasks (pinned to Gemini 3.1 Pro Preview). • Memory Fencing: Hermes's persistent memory and learning loops must remain enabled to accumulate facts and user preferences. However, the agent must be strictly fenced from self-editing or rewriting its own mechanical execution paths (portals, downloads, filings), which must remain frozen in MCP tool code. • Hardware Deployment Infrastructure: • Always-on Brain: M1 Pro MacBook Pro (16 GB, mains-powered, lid open) running the Hermes gateway, Messages.app, and a BlueBubbles iMessage bridge. Must be fully automated via launchd services to handle headless crash recovery, auto-login, and sleep prevention (pmset autorestart / caffeinate). • Tools and Storage: Synology NAS (10.0.0.149) hosting the Lawfather MCP container, local client folders, and Drive sync. • Private Network: Tailscale mesh across all devices for secure remote access without open inbound ports. Acceptance Criteria for Sign-Off • No batch operation requires the caller to iterate. • The case resolver returns ranked candidates and never auto-selects. • Transcription runs seamlessly as an async two-stage job surviving multi-hour files without timing out. • OCR never fires automatically on low-readability files without gated confirmation. • Zero regressions on the existing MCP tool inventory. • The Resiliency Test: The full stack successfully restarts completely unattended after a host reboot or simulated power loss, and is reachable via iMessage/SMS immediately after. • Self-editing is fenced on mechanical download/filing paths. Hard Guardrails • Privilege: Downloads route strictly to the correct client folder; a wrong-case match is treated as a severe defect, not a warning. Privileged audio/discovery data stays on owned hardware where the chosen model allows. • Determinism: Repeatable steps live entirely in tool code, never in prompts. • Agnosticism: Model and host layers must remain fully swappable without modifying the core MCP tools. Before quoting "done," you will be expected to confirm live portal behaviors regarding District Clerk document labels, DA portal stable identifiers, and county search surfaces. How to Apply Please submit a proposal detailing your specific experience with MCP architectures, Playwright browser automation, and macOS/Docker DevOps automation. Anti-Bot Filtering: To prove you read this entire scope, please start your application with the phrase "PROTECT THE LAW" in all caps. Automated or generic copy-paste applications will be instantly rejected.

Texas Municipality Data Collection Tool Built a custom web scraping and data aggregation system to collect and organize public information from Texas municipal websites. The tool automated data extraction across multiple sources, standardized the results, and exported structured datasets for analysis and reporting. Technologies: React, Node.js, Web Scraping, APIs, Data Processing, MongoDB/PostgreSQL

I need a Discord bot built that posts positive expected value (+EV) sports betting picks to a channel, plus esports match schedules/scores. I have the full technical spec already written — APIs picked, EV formula defined, architecture outlined. This is integration work, not research. What's provided: Working API keys for The Odds API (sports odds) and PandaScore (esports stats) — I'll provide on hire Complete EV calculation formula (Python, ready to use) Full architecture spec (polling schedule, caching approach, bookmaker lists) Core deliverables (must-have, fixed price): Discord bot that connects to my server Scheduled polling (1-2x daily, not live) of The Odds API for sports moneylines + player props EV calculation comparing soft-book odds (DraftKings/FanDuel/Caesars) against Pinnacle as the sharp reference Caching layer (database) so the bot never calls the API live per Discord command Bot posts flagged +EV picks to a designated channel, above a configurable EV threshold PandaScore integration for esports match schedules/results posted to a separate channel Basic error handling with retry/backoff (no runaway API costs) Documentation: how to run it, how to add new sports/leagues, how to change the EV threshold Stretch goal (only if time allows within budget — not required): OddsPapi integration for esports moneyline EV detection (this API is unverified/free-tier, so treat as experimental) Tech preferences: Python or Node.js, whichever you're stronger in. Open to your hosting recommendation (needs to run 24/7 cheaply). Budget & Payment Structure: $500 fixed price, split into milestones Milestone 1 ($150) — Foundation: Discord bot connects to server, The Odds API integration pulling live sports odds data, caching layer working. Paid on demo of working data pull + bot online in server. Milestone 2 ($200) — Core Logic: EV calculation implemented and verified accurate against manual spot-checks, picks posting to Discord channel automatically on schedule. Paid on demo of at least 3 correctly-calculated +EV picks posted live. Milestone 3 ($150) — Esports + Polish: PandaScore esports schedule/results integration, error handling/retry logic, documentation delivered. Paid on final delivery + handoff call. To apply: Tell me your estimated hours for each milestone, and confirm you've worked with Discord bots + REST API integrations before.