Description
Summary Project: AI Integration for Existing Web Application Engagement type: Contract / project-based (small agency or independent consultant) Location: United States-based preferred Budget: Small business budget — please quote fixed-price or capped hourly for defined scope Start: Flexible, pilot sprint preferred before full engagement About the project We run a web application built on: • Frontend: React • Backend: Node.js and Java • Database: PostgreSQL • Infrastructure: AWS We're looking to integrate AI into this existing system to reduce manual data updates and add intelligent features — automation, smart search/recommendations, and reduced manual maintenance overhead. We are a small company with a limited budget and are looking for a small, senior-led team or independent consultant who can deliver production-quality work without enterprise-agency overhead or pricing. What we need help with • Auditing our current architecture and recommending where AI adds the most value with the least complexity • Setting up vector search / retrieval (e.g. pgvector in PostgreSQL) for semantic search or RAG use cases • Integrating AWS AI services (Bedrock and/or SageMaker) into our Node.js/Java backend • Building automation (e.g. AWS EventBridge + Lambda) so routine data updates happen automatically instead of manually • Adding AI-powered features to the React frontend (e.g. smart suggestions, summarization, natural-language search) • Ensuring the solution is cost-aware — we need ongoing AWS/AI usage costs kept lean, not just the build cost Ideal candidate / team • Small shop (roughly 2–15 people) or independent senior consultant — not a large offshore agency • Demonstrable senior-level experience: has personally built and shipped production systems with this stack, not just managed a team that did • Hands-on experience integrating LLMs/AI services into an existing production application (not just greenfield AI demos) • Comfortable working with a small business budget and scoping work in phases rather than one large fixed engagement • Clear, direct communicator — able to explain technical tradeoffs in plain language • U.S.-based (or U.S. business entity) preferred for time zone alignment and contracting simplicity What we'll provide • Access to existing codebase, architecture docs, and AWS environment (under NDA) • A single point of contact for requirements and feedback • Clear priorities on which features matter most, once we've discussed scope Engagement structure we're proposing 1. Discovery / architecture review (paid, fixed fee) — assess our system and propose a phased AI integration plan with rough cost estimates (build + ongoing AWS/AI usage) 2. Pilot sprint (1–2 weeks, fixed scope) — implement one narrow AI feature end-to-end to evaluate fit before committing further 3. Phased build-out — based on pilot results, scope remaining work in defined phases How to apply / respond Please share: • 2–3 past projects with a similar stack (Postgres + AWS + AI/LLM integration), ideally with what you built and the outcome • Your team size and who would actually be working on this project • Your typical pricing structure (hourly, fixed-fee, retainer) and rough budget range you work within • Availability and expected timeline for a discovery call We're prioritizing fit and communication over lowest price — we'd rather pay fairly for a small team that gets it right than the cheapest bid.