AI Engineer: Agentic AI & Tooling Architect

SHOPEE IP SINGAPORE PRIVATE LIMITED; Singapore; On-site; SGD 60,000 - 100,000; Full time

Job summary

Shopee IP Singapore Private Limited is recruiting for an AI workflow design specialist to design and optimize agent architectures and tooling for a user-facing product.

You will build and deploy APIs for agent lifecycle, improve memory and tool-use accuracy, and manage data collection and annotation workflows for post-training data. Prior experience with RAG, multimodal agents, and RL is preferred.

Qualifications

• Master’s in Computer science, Engineering, Information systems, or a related field.
• Minimum 1 Year of full time working experience in AI workflow design, RAG, workflow design and optimization for a user facing AI product.
• Minimum 1 Year of full time experience with multimodal agents and Reinforcement learning or model training.
• Experience with E-commerce platform and agents will be highly preferred.

Responsibilities

• Agentic Workflow: Design and implement core Agent architectures and Agent tooling
• API integration & Deployment: Build and optimize API’s for Agent lifecycle and deployment for runtime access.
• Memory & Tools: training optimization in Agent and Tool-use directions, improving metrics such as tool-calling accuracy, multi-turn instruction following, and hallucination control.
• Data & Evaluation: Manage the collection, cleaning, synthesis, and annotation workflows for post-training data; participate in annotation guideline development and vendor coordination.

Skills

AI workflow design

RAG workflows

Multimodal agents

Reinforcement learning

E-commerce familiarity

Education

Master’s degree in Computer Science or related field

Job description

Shopee IP Singapore Private Limited is recruiting for an AI workflow design specialist to design and optimize agent architectures and tooling for a user-facing product.

You will build and deploy APIs for agent lifecycle, improve memory and tool-use accuracy, and manage data collection and annotation workflows for post-training data. Prior experience with RAG, multimodal agents, and RL is preferred.