AI-Powered Catalog Search With Custom Ranking Logic

Overview We run a continuing legal education (CLE) platform with a large catalog of courses (live, replay, and on-demand) across dozens of practice areas. We need a developer to build an AI-powered catalog search that returns relevant classes for natural-language queries and applies a specific, already-defined ranking and grouping logic. The UI is designed and a written ranking spec is finalized — we'll share both with shortlisted candidates. We want a working v1 live quickly, then iterate. What you'll build Natural-language / semantic search over our course catalog, filterable by practice area, topic, credit type, and jurisdiction. A ranking + fill engine that follows our spec exactly (summary below). A clean, documented API the existing front end calls. The ranking logic (already specced — this is the core of the job) Results are filled by priority order, not blended relevance: Format tiers: Live + Replay are one combined tier and always rank above On-demand. Sort within tiers: Live/Replay by date (nearest upcoming first); On-demand by popularity. (We supply the popularity list.) Fill: show the total match count (e.g., "80 classes match"), render 10 — walk Live/Replay by date first, top up with most-popular On-demand, then link to the full set ("See all 80"). Grouping: 3 or fewer results = flat list; more than 3 = group by format tier, then sub-practice area. You don't have to design this logic — you have to implement it faithfully. The full spec is a few pages and will be provided. Stack We use the Anthropic Claude API and are open to your recommendation on vector store and embeddings (pgvector, Pinecone, Qdrant, etc.). Use whatever ships a clean v1 fastest. Required Production experience building semantic / AI search. Comfortable with vector databases, embeddings, and LLM APIs. Can implement precise ranking/sorting/grouping rules from a written spec. Can expose a clean, documented API for a React front end. Nice to have Legal or other accuracy-critical content experience. n8n, WooCommerce/Stripe familiarity. Engagement Type: [Hourly / Fixed-price — choose one] Timeline: Start now, working v1 live quickly. Budget: [Insert range, or "propose based on scope"] To apply, briefly tell us A search system you've built, and the corpus size. How you'd get a basic working version live fast. Your suggested vector store, embedding model, and LLM.