Our Company is hiring an AI Application Engineer with hands-on experience in delivering real-world LLM-powered systems. This role focuses on engineering, system design, and production deployment of AI applications rather than research-only work. You will own or co-own the full lifecycle of AI projects, including model selection, RAG architecture, multi-agent orchestration, prompt workflows, and system optimization, translating cutting-edge AI capabilities into scalable business solutions.

This is a global hiring role. We welcome candidates worldwide with proven AI project delivery experience.

Responsibilities

AI Application Development & Delivery

• Lead or co-own AI projects from requirement analysis, architecture design, to production deployment.
• Fine-tune, align, and optimize general LLMs, embedding models, and inference pipelines.
• Design structured and reusable Prompt Engineering workflows to improve task reliability and performance.

Multi-Agent Systems & Reasoning Frameworks

• Build and orchestrate multi-agent workflows using LangChain, LangGraph, MCP, or similar frameworks.
• Implement reasoning paradigms such as ReAct, Chain-of-Thought (CoT), Tree-of-Thought (ToT) to enhance agent decision quality and controllability.
• Integrate or evaluate agent platforms such as Coze, FastGPT, Dify when applicable.

RAG & Knowledge Systems

• Design and implement Retrieval-Augmented Generation (RAG) architectures.
• Build document knowledge retrieval systems using vector databases (Milvus, FAISS, Chroma).
• Continuously improve retrieval quality, context relevance, and reasoning accuracy.

Technical Research & Knowledge Sharing

• Track emerging AI trends (model alignment, multi-agent systems, multimodal models).
• Contribute to internal documentation, benchmarks, prototypes, or technical sharing.

Qualification

• Bachelor’s degree or above in Computer Science, AI, or a related field.
• Proven experience delivering at least one end-to-end AI application (LLM / RAG / Agent system).
• Hands-on experience with Prompt Engineering, LangChain, or RAG frameworks.
• Experience designing multi-agent architectures, preferably with LangGraph or MCP.
• Familiarity with vector database selection and integration.
• Strong understanding of ReAct-style agent workflows.

Nice to Have

• Practical experience with LoRA / QLoRA, model alignment, or inference optimization.
• Experience in model training or reinforcement learning fine-tuning.
• Open-source contributions, technical blogs, or internal/external tech sharing.
• Strong cross-functional communication skills.