Job description for AI Engineer at DigiSpark
Requirements:
- Hands-on experience implementing open-source AI models in on-premise or private infrastructure environments.
- Solid understanding of Large Language Models (LLMs), including basic architecture, inference, fine-tuning, and deployment.
- Familiarity with Retrieval-Augmented Generation (RAG) concepts, including ingestion pipelines, embeddings, retrieval, and generation workflows.
- Experience or understanding of vector databases (e.g., FAISS, Milvus, Weaviate, or similar) for semantic search and knowledge retrieval.
- Understanding of Model Context Protocol (MCP) or general mechanisms for integrating AI models with tools, APIs, and external systems.
- Ability to deploy AI models using containerization technologies such as Docker and orchestration platforms like Kubernetes is a plus.
- Basic knowledge of API development (REST or gRPC) for integrating AI services into applications.