AI Engineer (LLM Applications)

Role overview Design and deliver applications built around large language models, turning model capabilities into useful product features. The work spans retrieval-augmented generation, agent-based systems, evaluation workflows, and deployment, with attention to application quality and operating cost.

Responsibilities - Build and deploy LLM application systems, including RAG and agent workflows. - Create evaluation pipelines to assess application behavior and model output. - Apply prompt design and evaluation practices to improve system performance. - Consider cost and efficiency when shaping and operating model-powered features. - Connect AI capabilities to product use cases through backend application development.

Requirements - Hands-on experience with LLM applications or machine-learning systems; personal projects are acceptable. - Fluent Python skills. - Experience with at least one web backend framework. - Practical understanding of prompt engineering, evaluation, and cost optimization.

Benefits and work setup - Full-time remote role, open to candidates in Taiwan or working remotely.