AI Agent Application Algorithm Engineer

Shopee; Singapore; On-site; SGD 80,000 - 120,000; Full time

Job summary

Shopee in Singapore is recruiting for roles in their new strategic AI department focused on developing innovative applications and enhancing human connection through generative AI. Candidates should hold a Master's in computer science or similar, or have strong industrial experience. Key responsibilities include designing core architectures and optimizing agents for productivity.

The ideal candidate should have a deep understanding of agent frameworks and experience in RAG systems. Strong skills in prompt engineering are essential for this cutting-edge position.

Qualifications

• Deep understanding of Agent frameworks.
• Experience in RAG and vector retrieval.
• Proficiency in managing LLM capability boundaries.

Responsibilities

• Design and implement core Agent architectures.
• Architect advanced RAG systems for hybrid search.
• Develop long/short-term memory systems.

Skills

Agent frameworks (LangChain, LlamaIndex, ADK)

RAG systems

Prompt Engineering

LLM capability management

Education

Master’s in computer science or related fields

Job description

Sea Group is establishing a brand-new, strategic AI department. This department is dedicated to exploring the transformative potential of generative AI in revolutionizing human connection, self-expression and communication diversity, and social interaction. We are building the next generation of AI-native applications and a comprehensive Model-as-a-Service (MaaS) product support system. Based on massive multi-country data, we are building a leading multilingual AI ecosystem from the ground up. We look forward to more outstanding talents joining us to build leading Southeast Asian multilingual models and explore innovative AI-native applications.

The AI application team focuses on the intersection of social connectivity and artificial intelligence. Our mission is to leverage LLMs to create digital personas that can act as personal assistants and social bridges. This team operates with a startup's agility backed by our Group's robust resources, aiming to define how humans interact in the AI era.

About the Job

• Agentic Workflow: Design and implement core Agent architectures, including task planning, state tracking, and multi-turn conversation management.
• Agentic RAG: Architect advanced RAG systems supporting hybrid search (BM25 + Embedding) and LLM-driven proactive retrieval.
• Memory & Tools: Develop long/short-term memory systems and tool-call/plugin dispatching (ADK framework integration).
• End-to-End Delivery: Optimize intent recognition accuracy, task completion rates, and system latency for production-grade Agents.

Requirements:

• Master’s in computer science, natural language processing or related fields; Bachelor can be considered with a strong industrial experience.
• Deep understanding of Agent frameworks (LangChain, LlamaIndex, ADK).
• Experience in RAG, vector retrieval, and Reranker model optimization.
• Proficiency in Prompt Engineering and managing LLM capability boundaries.
• Experience in personal assistants or productivity tools (Calendar, Memo, Info-integration).