LLM Developer

Project that you will be working on: https://giostech.comCompany DescriptionGiosTech is an innovation-focused startup building a platform that adds persistent memory and web tracking to LLM-based applications like ChatGPT. We're looking for a hands-on LLM Engineer to help us build core backend infrastructure that manages user session memory and enriches LLM responses with real-time web data.If you're passionate about making large language models smarter, more useful, and context-aware — and you know your way around APIs, databases, and token windows — we'd love to work with you.ResponsibilitiesDesign and implement memory systems for storing and retrieving chat history in LLM applicationsBuild APIs that wrap ChatGPT, Claude, and other models with thread-based context managementImplement optional web tracking, allowing users to pass in search results or session metadata to improve LLM accuracyOptimize token usage via summarization, chunking, and context trimmingWork with the founder to define product architecture, performance targets, and security measuresQualificationsStrong experience with OpenAI, Anthropic, or similar LLM APIsExperience building context-aware systems using threads, sessions, or retrieval techniquesFamiliar with PostgreSQL, Supabase, or other modern backend stacksComfort working with web scraping, Bing/Google search APIs, or Perplexity-style retrievalUnderstanding of prompt engineering, token budgeting, and LLM limitations(Bonus) Knowledge of vector search, function calling, or LangChain/RAG systems