Job Title: Full Stack Developer (LLM App Development - Consulting Role - On demand)
We are seeking a Full Stack Developer to work closely with our COO in developing LLM-based applications with unlimited contextual memory. You’ll collaborate directly with our COO to create prototypes for mobile, web, and native apps, using the latest tools in AI-driven app development. This is a flexible, on-demand consulting role, ideally suited for a developer who can commit 2-hour sessions on an as-needed basis.
Responsibilities:
- Prototype Development: Collaborate with the COO to build LLM app prototypes, using tools like Bolt.new, Cursor, or Replit for quick iteration.
- AI Model Integration: Develop a chatbot as part of an LLM-based web app MVP using models like OpenAI’s ChatGPT, Gemini, or Claude Sonnet 3.5.
- Responsive Design: Create responsive web applications that provide seamless experiences across desktop and mobile devices.
- Contextual Memory: Implement a vector database solution such as PGVector DB or Pinecone DB for Retrieval-Augmented Generation (RAG), enabling long-term contextual memory for the app.
- SaaS Features: Design the MVP with SaaS capabilities, considering scalability and multi-tenant support.
- Multimodal Search: Enable multimodal functionality to search structured and unstructured data formats (Excel, audio, video, PDF, text, Word documents, etc.) using AI agents.
- Cloud Deployment: Deploy solutions on AWS, GCP, or Azure, ensuring scalability and secure access.
- Experimental Tools: Work with tools like Google’s Notebook LM and potentially integrate other emerging technologies.
Preferred Qualifications:
- Proficiency in Full Stack Development: Strong skills with frameworks and tools for both front-end and back-end development. Familiarity with React.js or Vue.js for front-end and Node.js or Django for back-end is a plus.
- Experience with LLMs and Vector Databases: Previous experience building LLM-based applications with vector databases (e.g., PGVector DB, Pinecone DB) for RAG.
- Familiarity with Cloud Services: Comfortable deploying and managing apps on AWS, GCP, or Azure.
- Familiarity with AI Tools: Experience with LangChain for integrating large language models, and comfort with tools such as Bolt.new, Cursor, and Replit.
- Multimodal AI Integration: Experience with multimodal AI features (image, video, text, etc.) and familiarity with AI agents.
This is a consulting role on a 1099 basis with flexibility to work on cutting-edge AI applications. Join us for the opportunity to enhance your AI expertise significantly through real-world challenges! |
