Full-Stack AI Developer – Engineer

This is a fully remote position, open to applicants in Germany.

📋 Description

• Design and develop the server-side RAG pipeline, encompassing query processing, embedding, vector search, and prompt construction.

• Create both frontend and backend components while ensuring that all LLM API interactions are exclusively server-side.

• Implement a three-tier subscription model, featuring a 7-day trial, using Stripe.

• Establish robust webhook functionality for tier validation directly within the database.

• Develop an automated pipeline that transcribes new audio and video content through the Whisper API, processes it, divides it into manageable chunks, and uploads it to the vector database.

• Create an internal behavioral analytics dashboard for real-time tracking of search queries, emotional tone, content gaps, and usage limits.

• Ensure that technical decisions are in alignment with the Project Lead.

⛳️ Requirements

• Significant experience in developing modern full-stack web applications, preferably using our chosen tech stack: Next.js (React) for frontend and Node.js (Express or Next.js API Routes) for backend.

• Hands-on experience in constructing RAG systems, managing vector databases (such as Pinecone or Weaviate), and utilizing LLM APIs, particularly Anthropic Claude Sonnet and OpenAI.

• Strong expertise in PostgreSQL (e.g., via Supabase) and authentication solutions like Clerk or Supabase Auth.

• Experience with secure Stripe integration, including handling subscriptions, dunning processes, and webhooks.

• A solid understanding of security practices: API keys and rate limits must be managed and enforced strictly on the server side.

• Capability to work independently within a stringent 12-week build-to-launch timeline while proactively aligning technical decisions with the Project Lead.

• A GitHub profile and relevant references in RAG or full-stack development are welcome but not mandatory.

🏝️ Benefits

• 100% remote: Enjoy flexible work from any location.

• Cutting-edge technology: Engage with a truly innovative RAG AI system utilizing modern LLMs and a contemporary tech stack.

• Responsibility and impact: Contribute significantly to the development of a highly visible product post-launch.

• Efficiency: Benefit from short communication lines with direct access to the Project Lead.

• Long-term prospects: Opportunity for continued collaboration on maintenance and further development following a successful launch.