Generative AI Engineer

LangChain provides components for retrieval pipelines, document loading, chunking, and vector-store integration that fit this kind of workflow.\nIntegrate quantized GGUF models with local inference runtimes such as llama.cpp. llama.cpp supports GGUF models, multiple quantization levels, local serving, and CPU/GPU hybrid inference for running models efficiently on local hardware.\nOptimize AI pipelines for edge and offline deployment, ensuring reliable inference on resource-constrained systems.\nImplement multilingual semantic search using embedding models such as paraphrase-multilingual-MiniLM-L12-v2, which supports multilingual text embeddings across many languages.\nBuild and manage local vector stores using FAISS or similar retrieval systems for similarity search and contextual grounding. FAISS is designed for efficient similarity search over dense vectors and is commonly used in RAG systems.\n\nPreferred Skills\nExperience with edge AI deployment and offline AI systems\nFamiliarity with local inference servers and OpenAI-compatible local APIs.

llama.cpp includes a local API server option for serving models through HTTP.\nExperience with Hindi-English multilingual NLP\nExperience in education AI, EdTech, tutoring systems, assessment systems, or curriculum-based AI tools\nFamiliarity with prompt engineering, LoRA/QLoRA fine-tuning, and evaluation pipelines\nExperience with semantic search, embeddings, and local knowledge-base systems\n\nEducational Qualifications\nBachelor’s or Master’s degree in Artificial Intelligence, Computer Science, Data Science, Machine Learning, or a related field\n\nWhy Join LearningBIX\nWork on meaningful AI products for education\nBuild real-world offline AI systems that can impact schools and students\nCollaborate with an innovation-driven team focused on STEM and future-ready learning\nBe part of a mission-led company using technology to improve education outcomes