AI Agent Algorithm Engineer

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

Job Description

• Build core Agent logic, including but not limited to task planning and orchestration, tool calling, multi-turn dialogue management, memory, RAG, context engineering, and multi-agent collaboration.
• Lead Continuous Pre-training and Post-training for vertical domains and business scenarios, including building high-quality datasets and data pipelines, designing RL reward models, improving instruction following and reasoning capabilities, task completion, role-playing, anthropomorphic and personalized dialogue, proactive/reactive immersive multimodal conversation experiences, and enhancing the model's IQ and EQ.
• Build long-term and short-term memory architectures, addressing issues such as forgetting and attention dispersion in long contexts, and improving immersion and consistency in long-term user interactions.
• Build multimodal RAG systems, including development and optimization of key modules such as recall, ranking, long-text processing, and multi-document synthesis.
• Design and tune prompts and context management, with tailored optimization for different product requirements.
• Design scientifically rigorous quantitative evaluation systems and plans aligned with product requirements; continuously monitor product metrics and provide guidance for Agent and model optimization.
• Develop the Agent's tool layer, integrating external APIs and MCP such as search, code interpreters, browsers, sandboxes, and third-party services.
• Explore innovative AI applications.

Requirements

• Master's degree or above in Artificial Intelligence, Computer Science, Mathematics, or a related field.
• At least 2 years of full-time industry experience building and deploying production multi-agent LLM systems (task planning, orchestration, tool calling).
• Hands‑on experience fine‑tuning LLMs via SFT and DPO, combined with hands‑on experience building and optimizing RAG/retrieval systems (recall, ranking, embedding fine‑tuning).
• Good programming skills; proficient in Python
• Good problem solving analysis and resolution skills; sustained interest and curiosity in frontier AI technologies and applications; strong self‑drive; able to collaborate closely with teams to drive a full closed loop from research to deployment.
• Good development experience with Agent frameworks such as LangGraph, Google Agent Development Kit, OWL, or AutoGen.