Job Description
7 days ago
We are looking for an AI Engineer specializing in LLMs and autonomous agents. Your mission is to build "intelligent brains" that can interact with complex datasets, answer user queries with high precision, and automate multi-step business workflows. You will bridge the gap between raw data and actionable insights through natural language.
What You’ll Be Doing?
• AI Agent Development : Design and implement autonomous agents using frameworks like LangChain, LlamaIndex, or PydanticAI , enabling "Tool Calling" for external system interactions.
• Data Reasoning & RAG : Build advanced Retrieval-Augmented Generation (RAG) pipelines to provide accurate answers based on structured (SQL) and unstructured data.
• Advanced Prompt Engineering : Develop sophisticated prompt strategies (e.g., Chain-of-Thought, ReAct) to enhance reasoning capabilities for data reporting and analysis.
• System Integration : Build and maintain scalable backend APIs (FastAPI/Python) to serve AI features while ensuring data security and real-time response.
What We’re Looking For?
• Experience : 3+ years in software development, with at least 1-2 years of hands-on experience in LLM/GenAI applications.
• Tech Stack : Proficiency in Python and experience with Vector Databases (e.g., Qdrant, Pinecone, Milvus).
• Proven Track Record : Experience in implementing Text-to-SQL , automated workflows, or multi-turn conversational agents.
• Quality Control : Knowledge of evaluation frameworks to measure model accuracy and mitigate hallucinations.
• More experienced candidates will be considered as Senior AI Engineer.
What You’ll Be Doing?
• AI Agent Development : Design and implement autonomous agents using frameworks like LangChain, LlamaIndex, or PydanticAI , enabling "Tool Calling" for external system interactions.
• Data Reasoning & RAG : Build advanced Retrieval-Augmented Generation (RAG) pipelines to provide accurate answers based on structured (SQL) and unstructured data.
• Advanced Prompt Engineering : Develop sophisticated prompt strategies (e.g., Chain-of-Thought, ReAct) to enhance reasoning capabilities for data reporting and analysis.
• System Integration : Build and maintain scalable backend APIs (FastAPI/Python) to serve AI features while ensuring data security and real-time response.
What We’re Looking For?
• Experience : 3+ years in software development, with at least 1-2 years of hands-on experience in LLM/GenAI applications.
• Tech Stack : Proficiency in Python and experience with Vector Databases (e.g., Qdrant, Pinecone, Milvus).
• Proven Track Record : Experience in implementing Text-to-SQL , automated workflows, or multi-turn conversational agents.
• Quality Control : Knowledge of evaluation frameworks to measure model accuracy and mitigate hallucinations.
• More experienced candidates will be considered as Senior AI Engineer.
More jobs from Varadise Limited

Product Manager (SaaS Platform & Delivery)
Varadise Limited
Product/Project Manager
Central and Western, Hong Kong, China
7 days ago
Full Time
Onsite
Technology, Information and Media

DevOps Engineer (Mid-Level)
Varadise Limited
jobBoard.filter.role.option.DEVOPS_SRE
Central and Western, Hong Kong, China
7 days ago
Full Time
Onsite
Technology, Information and Media

AI Engineer (Computer Vision & Edge AI)
Varadise Limited
Software Engineer
Central and Western, Hong Kong, China
7 days ago
Full Time
Onsite
Technology, Information and Media
More jobs like this
AI Engineer Agentic Systems & LLM Architecture Hong Kong
Unspecified
Central and Western, Hong Kong, China
Agentic AI Engineer - RAG & Data Pipelines
GEARFACTORY.AI LIMITED
Central and Western, Hong Kong, China
🎉 Got an interview?






