Global AI Application Engineer

TEKsystems; Hong Kong; On-site; HKD 900,000 - 1,300,000; Full time

Job summary

TEKsystems is hiring an AI Application Engineer to join a growing AI team within a global retail organization. You will develop GenAI and Agentic AI solutions for real business use cases across Global Business Units, owning the entire AI application lifecycle from requirements to production deployment.

This hands-on role emphasizes strong engineering fundamentals, Python, and exposure to LangGraph/LangChain.

Qualifications

• Production-grade AI applications experience.
• Strong Python and software fundamentals.
• Hands-on with LLMs, RAG, agentic AI, tool/function calling.

Responsibilities

• Design and build production-grade GenAI and Agentic AI applications.
• Develop multi-step agent workflows with tool calling, state management, routing, retries, checkpoints, and human-in-the-loop.
• Build agent orchestration using LangGraph, LangChain, or similar frameworks.
• Design and optimize RAG, vector search, retrieval, reranking, and context-management solutions.
• Integrate AI applications with enterprise APIs, databases, search services, and frontend apps.
• Build scalable backend services using Python and FastAPI.
• Evaluate AI outputs for accuracy, latency, and cost.
• Implement testing, tracing, and observability for production AI apps.
• Improve system reliability, security, and performance.
• Collaborate with Product, Data Science, Engineering, and Business teams.

Skills

Python

FastAPI

GenAI

Agentic AI

LangChain

LangGraph

LLMs

Vector search

API integration

Tools

LangGraph

LangChain

Job description

We are hiring an AI Application Engineer to join a growing AI team within a global retail organization, developing advanced GenAI and Agentic AI solutions for real business use cases for Global Business Units.

This is a hands-on engineering role with strong technical ownership. You will work across the full AI application lifecycle, from understanding business requirements and designing the solution through implementation, integration, evaluation, production deployment, monitoring, and continuous improvement.

What You’ll Do

Design and build production-grade GenAI and Agentic AI applications

Develop multi-step agent workflows involving tool calling, state management, routing, retries, checkpoints, and human-in-the-loop

Build agent orchestration using LangGraph, LangChain, or similar frameworks

Design and optimize RAG, vector search, retrieval, reranking, and context-management solutions

Integrate AI applications with enterprise APIs, databases, search services, and frontend applications

Build scalable backend services using Python and FastAPI

Evaluate AI outputs for accuracy, relevance, hallucination, latency, and cost

Implement testing, tracing, monitoring, and observability for production AI applications

Improve system reliability, scalability, security, and performance

Work closely with Product, Data Science, Engineering, and Business teams

What We’re Looking For

Proven experience building and deploying AI applications into production

Strong Python and software engineering fundamentals

Hands-on experience with LLMs, RAG, Agentic AI, and tool/function calling

Experience with LangGraph, LangChain, or equivalent orchestration frameworks

Experience building APIs and integrating AI applications with enterprise systems

Able to work proactively and independently with strong end-to-end ownership

Strong communication skills and ability to explain technical decisions and trade-offs clearly

Equivalent technologies are welcome. The focus is on strong engineering fundamentals and real AI production experience.