Applied AI Engineer

We are seeking an experienced and forward-thinking AI Engineer to lead the design, development, and production deployment of our AI systems for Global Financial Market business. In this role, you will bridge the gap between advanced research and production-grade software engineering, with a heavy focus on multi-agent workflows.

Job Responsibilities:

1. Leadership & Stakeholder Management

• Leadership: Act as the subject matter expert for Agentic engineering. Guide the overarching AI technology stack selection, system architecture design, and long-term engineering excellence.

• User & Requirement Alignment: Collaborate closely with product management and end-users to translate complex business workflows and user needs into concrete multi-agent requirements.

• Team Mentorship: Mentor and upskill engineering team members on LLM architectures, prompt engineering, asynchronous backend development, and AI engineering best practices.

2. Multi-Agent & LLM Engineering

• Agent System Design: Design and deploy Agents from 0 to 1. Own the architecture design, Tool/Function Calling implementations, multi-Agent collaboration protocols, and complex Workflow orchestrations.

• Framework Implementation: Leverage LLM ecosystems and SDKs to build robust corporate solutions using MCP and Agentic Workflows.

• AI Evaluation: Build and construct automated evaluation pipelines to validate non-deterministic agent behaviors, optimize decision-making accuracy.

3. Backend & Distributed Systems Infrastructure

• Production Services: Architect, develop, test, and deploy highly concurrent, high-availability, production-grade Web Services. Independently complete backend service infrastructure.

• System Optimization: Build and optimize high-performance distributed systems, driving system performance optimization and engineering excellence across the entire stack.

• DevOps & Deployment: Utilize containerization technologies like Docker and OpenShift to complete application deployment, scaling, and daily operations.

Job Requirements:

1. Experience & Track Record

• Experience: Approximately 10 years of professional working experience.

• AI Focus: The latest 4–5 years must be specifically dedicated to the AI domain, with a proven track record in LLM and Agent technologies

• Project Track Record: Must have 3+ years of hands-on AI-related experience, with active participation in at least 3 real-world production-grade deployment projects. At least 1 project must be a complex Multi-Agent, Agentic Workflow

2. Technical Skills & Tech Stack

• Languages & Core Backend: Expertise in Python, advanced asyncio, and FastAPI, with a proven track record of designing high-concurrency, high-availability backend architectures.

• AI & Multi-Agent Frameworks: Hands-on proficiency with LangGraph, CrewAI, AutoGen, LangChain, LlamaIndex, Google ADK, and Claude SDK

• LLM Core & Protocols: Deep understanding of model inference, Prompt Engineering, Tool/Function Calling, Model Context Protocol (MCP), and Agentic Workflows.

• DevOps & Infrastructure: Experience in distributed system development, building/maintaining complete CI/CD pipelines, and using containerization tools like Docker and OpenShift for deployment and operations.

Location:

Guangzhou (DTC)

Job:

Technology

Schedule:

Regular

Employee Status:

Full time