Backend Developer LLM & Vector Database Integration Internship

We are seeking a backend developer with experience in integrating open-source LLMs (e.g., Mistral, LLaMA) and vector databases (such as FAISS, Qdrant, Weaviate, Milvus) in offline or edge environments. As part of the team, you will be involved in developing core APIs and infrastructure to facilitate embedding pipelines, retrieval-augmented generation (RAG), and LLM inference on local or mobile hardware. Your responsibilities will include designing and implementing backend services that connect with local LLMs and vector databases, creating APIs to support engineering, retrieval, and inference, integrating embedding models (e.g., BGE, MiniLM), and managing chunking/processing pipelines. Additionally, you will be optimizing performance for offline or constrained environments such as mobile and embedded devices, packaging and deploying models using frameworks like Ollama, llama.cpp, gguf, or on-device runtimes, as well as handling local file I/O, document ingestion, metadata tagging, and indexing. About the Company: Infoware is a process-driven software solutions provider that specializes in tailored software solutions. Our expertise lies in collaborating with enterprises and startups to deliver comprehensive end-to-end solutions. To learn more about our company, please visit our website at https://www.infowareindia.com/,