AI Engineer Lead/ Senior AI Engineer

ConnectedGroup; Hong Kong; Hybrid; HKD 900,000 - 1,300,000; Full time

Job summary

ConnectedGroup is seeking a Senior AI Engineer Leader in Hong Kong to design and deliver production-grade AI solutions for our banking clients. You will architect AI agent platforms, implement RAG/GraphRAG, knowledge graphs, and secure microservices, while collaborating with business stakeholders and architects.

The role emphasizes hands-on development in Python and Java/TypeScript, with cloud and DevOps practices, CI/CD, and containerization. Hybrid work is available in a banking setting.

Qualifications

• Bachelor's degree or higher in CS/Software/AI/Data Science or equivalent
• 5+ years in software or AI engineering shipping scalable enterprise backend services or automation platforms
• Proficiency in Python and at least one enterprise language (Java/TypeScript/JavaScript/Go)
• Hands-on experience building LLM applications, prompt orchestration, function calling, memory, and evaluation frameworks

Responsibilities

• Design and build production-grade AI solutions and agentic workflows
• Develop AI knowledge augmentation using RAG, GraphRAG, embeddings, and Knowledge Graphs
• Create secure, scalable backend services and APIs using Python/TS/Java
• Integrate AI tooling (Cursor, Claude Code, Copilot) for testing and solution generation
• Ensure governance, logging, telemetry, access control and production safety
• Implement CI/CD, containerization (Docker/Kubernetes) and cloud deployment

Skills

Python

Java

TypeScript/JavaScript

Go

LLM & AI engineering

Education

Bachelor's degree or above in Computer Science/Software Engineering/AI/Data Science

Tools

Docker

Kubernetes

LangChain

LangGraph

CI/CD

Job description

Senior AI Engineer/AI Engineer Lead (Banking Hybird)

Role Overview

We are seeking a hands-on Senior AI Engineer to design, build, and deliver production-grade AI solutions. You will build core capabilities for our AI Agent platform, engineer advanced retrieval mechanisms (RAG/GraphRAG), and develop secure microservices and APIs. Working closely with business stakeholders, product leads, and senior architects, you will bridge the gap between cutting-edge LLM architectures and production-ready enterprise applications.

Key Responsibilities

• AI Agent & Solution Development: Design and build production-ready LLM solutions, agentic workflows, task orchestration routines, and automated tools using Python and modern orchestration frameworks.

• RAG & Knowledge Engineering: Implement and optimize enterprise Knowledge Augmentation solutions, leveraging RAG, GraphRAG, vector embeddings, and Knowledge Graph integrations.

• Backend & API Engineering: Develop secure, scalable backend services, APIs, data pipelines, and user-facing features using Python, TypeScript/JavaScript, or Java.

• AI-Native Workflow Integration: Utilize and integrate AI coding tools (e.g., Cursor, Claude Code, Copilot) to streamline testing, documentation, and technical solution generation.

• Runtime Quality & Governance: Implement evaluation protocols, logging, telemetry, access control, and guardrails to ensure AI models and agents perform accurately and securely in production.

• CI/CD & Deployment: Apply robust engineering standards for testing, continuous integration/continuous delivery (CI/CD), containerization (Docker/Kubernetes), and cloud deployment.

• Stakeholder & Team Collaboration: Partner with business analysts, QA, security, and risk teams to gather requirements, review code, and ensure solutions meet strict enterprise guidelines.

• Production Support: Support application deployment, real-time monitoring, troubleshooting, and iterative system performance enhancements.

Qualifications & Experience

• Education: Bachelor's degree or above in Computer Science, Software Engineering, AI, Data Science, or equivalent practical experience.

• Professional Experience: 5+ years in software engineering or AI engineering, with a proven track record of shipping scalable enterprise backend services or automation platforms.

• Core Programming Skills: High proficiency in Python, plus working knowledge of an additional enterprise language ecosystem (e.g., Java, TypeScript/JavaScript, or Go).

• AI & LLM Architecture Experience:

  • Hands-on expertise building LLM applications, prompt orchestration, function calling, memory, and evaluation frameworks.

  • Practical experience using LangChain, LangGraph, or equivalent LLM orchestration frameworks.

  • Direct experience implementing enterprise RAG, vector databases, or GraphRAG.

• Engineering Best Practices: Solid understanding of microservices, RESTful APIs, database design, distributed systems, and security/privacy controls.

• Cloud & DevOps: Hands-on experience with Docker, Kubernetes, CI/CD, logging, and observability tools.