AI Application Engineer

Location: Shenzhen / hybrid remote

Responsibilities

• Design and implement prompts, retrieval, and evaluation pipelines; integrate OpenAI-compatible APIs.
• Build vector stores and RAG pipelines; handle chunking, permissions, and auditing.
• Work with product and backend to balance cost and latency.

Requirements

• 1+ year of related experience or strong personal projects.
• Proficient in Python; familiar with LangChain or custom orchestration.
• Understand embeddings and vector database fundamentals.

Nice to have

• Experience with on-prem deployment and sensitive data handling.
• Familiar with differences across models such as DeepSeek and Claude.

Photo from Unsplash; commercial use is allowed under their license.