Lead AI Agent Architect: LLM & RAG Systems

Shopee; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Shopee is seeking an AI systems engineer to design and deploy production multi-agent LLM systems, focusing on task planning, orchestration, and tool calling. You will shape memory architectures, RAG modules, and context management for robust long-term interactions.

You will integrate external APIs, tune prompts, and lead continuous improvement with strong emphasis on evaluation and product metrics. This role demands collaboration across teams and hands-on Python development.

Qualifications

• Master's degree or higher in AI, CS, Mathematics or related field.
• At least 2 years of full-time industry experience building production multi-agent LLM systems (task planning, orchestration, tool calling).
• Hands-on experience fine-tuning LLMs via SFT and DPO, and building RAG/retrieval systems (recall, ranking, embedding fine-tuning).
• Strong programming skills; proficient in Python.
• Experience with Agent frameworks such as LangGraph, Google Agent Development Kit, OWL, or AutoGen.

Responsibilities

• Build core Agent logic: task planning, tool calling, multi-turn dialogue, memory and RAG.
• Lead continuous pre-training and post-training for vertical domains and business scenarios.
• Develop memory architectures to address forgetting and long contexts for consistent user interactions.
• Create multimodal RAG systems, including recall, ranking and long-text processing modules.
• Design prompts and context management tailored to product needs.
• Design evaluation systems and monitor product metrics for Agent optimization.
• Develop the Agent's tool layer, integrating external APIs and third-party services.
• Explore innovative AI applications.

Skills

Analytical thinking

Problem solving

Team collaboration

Education

Master's degree or above in AI/CS/Math

Tools

LangGraph

Google Agent Development Kit

OWL

AutoGen

Python

Job description

Shopee is seeking an AI systems engineer to design and deploy production multi-agent LLM systems, focusing on task planning, orchestration, and tool calling. You will shape memory architectures, RAG modules, and context management for robust long-term interactions.

You will integrate external APIs, tune prompts, and lead continuous improvement with strong emphasis on evaluation and product metrics. This role demands collaboration across teams and hands-on Python development.