{"slug": "mission-rag-system-for-an-endangered-spoken-language-10-weeks-full-ip-transfer", "title": "[MISSION] RAG system for an endangered spoken language — 10 weeks — full IP transfer", "summary": "A client is seeking an experienced NLP/LLM engineer to build the first RAG-based localization engine for a low-resource South American language within 10 weeks, with full IP transfer and a budget of €5,000–€10,000.", "body_md": "Hi,\n\nI’m looking for an experienced NLP/LLM engineer for a serious, well-scoped project: building the first RAG-based localization engine for a low-resource language spoken in South America.\n\nThe project is built on a proprietary corpus (pedagogical content, dictionary, proverbs, orthographic rules) developed over 4 years. Architecture, endpoints, quality criteria and deliverables are fully specified in a detailed technical brief (available under NDA).\n\n**Technical scope (MVP — 10 weeks)**\n\n- RAG pipeline on low-resource language corpus (LangChain or LlamaIndex)\n- Multilingual embedding model (multilingual-e5 or equivalent)\n- Vector DB: Pinecone, Weaviate or Supabase pgvector — latency < 500ms\n- Modular prompt layer — 6 use-case templates (translate, educate, dub, subtitle, localize, campaign)\n- Multi-tenant B2B SaaS infrastructure — strict data isolation, JWT auth, configurable quotas\n- REST API + Swagger documentation\n- Admin interface for glossary management (no-dev updates)\n- Offline SQLite bundle for React Native mobile app\n\n**Profile required**\n\n- Proven RAG experience on low-resource or multilingual corpora\n- Multi-tenant SaaS architecture references\n- Modular prompt engineering in production (Anthropic or OpenAI API)\n- Full IP transfer to client — non-negotiable\n- NDA before corpus access\n- Budget: 5,000–10,000€ depending on experience\n- Start: within 2–3 weeks\n\nIf this matches your profile, please reply with concrete references on RAG low-resource languages, multi-tenant SaaS architecture, and modular prompt engineering in production", "url": "https://wpnews.pro/news/mission-rag-system-for-an-endangered-spoken-language-10-weeks-full-ip-transfer", "canonical_source": "https://discuss.huggingface.co/t/mission-rag-system-for-an-endangered-spoken-language-10-weeks-full-ip-transfer/177186#post_1", "published_at": "2026-06-26 16:40:42+00:00", "updated_at": "2026-06-26 16:41:15.310042+00:00", "lang": "en", "topics": ["natural-language-processing", "large-language-models", "ai-products", "ai-tools", "ai-infrastructure"], "entities": ["LangChain", "LlamaIndex", "Pinecone", "Weaviate", "Supabase", "Anthropic", "OpenAI", "React Native"], "alternates": {"html": "https://wpnews.pro/news/mission-rag-system-for-an-endangered-spoken-language-10-weeks-full-ip-transfer", "markdown": "https://wpnews.pro/news/mission-rag-system-for-an-endangered-spoken-language-10-weeks-full-ip-transfer.md", "text": "https://wpnews.pro/news/mission-rag-system-for-an-endangered-spoken-language-10-weeks-full-ip-transfer.txt", "jsonld": "https://wpnews.pro/news/mission-rag-system-for-an-endangered-spoken-language-10-weeks-full-ip-transfer.jsonld"}}