Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Tong Pei, a Master’s student in Artificial Intelligence at Vrije Universiteit Amsterdam with hands-on experience across LLM agent systems, RAG, knowledge graphs, and computer vision. I enjoy turning research insights into practical ML engineering solutions, and I’m currently building agent-centric platforms with public APIs and scalable memory architectures. I’ve designed episodic memory frameworks for multi-agent workflows, optimized LLM retrieval strategies, and reduced hallucinations and token usage in real-world tasks. Previously, I co-founded OmniMemory to deliver an Agent Memory SaaS and contributed to AIoT projects for smart furniture and home devices, including integrations with Xiaomi devices and an OpenClaw memory plugin for autonomous data read/write.…Hi, I’m Tong Pei, a Master’s student in Artificial Intelligence at Vrije Universiteit Amsterdam with hands-on experience across LLM agent systems, RAG, knowledge graphs, and computer vision. I enjoy turning research insights into practical ML engineering solutions, and I’m currently building agent-centric platforms with public APIs and scalable memory architectures. I’ve designed episodic memory frameworks for multi-agent workflows, optimized LLM retrieval strategies, and reduced hallucinations and token usage in real-world tasks. Previously, I co-founded OmniMemory to deliver an Agent Memory SaaS and contributed to AIoT projects for smart furniture and home devices, including integrations with Xiaomi devices and an OpenClaw memory plugin for autonomous data read/write.

Tong Pei

AI Engineer, AI Developer, Data Scientist, +2





Hi, I’m Tong Pei, a Master’s student in Artificial Intelligence at Vrije Universiteit Amsterdam with hands-on experience across LLM agent systems, RAG, knowledge graphs, and computer vision. I enjoy turning research insights into practical ML engineering solutions, and I’m currently building agent-centric platforms with public APIs and scalable memory architectures. I’ve designed episodic memory frameworks for multi-agent workflows, optimized LLM retrieval strategies, and reduced hallucinations and token usage in real-world tasks. Previously, I co-founded OmniMemory to deliver an Agent Memory SaaS and contributed to AIoT projects for smart furniture and home devices, including integrations with Xiaomi devices and an OpenClaw memory plugin for autonomous data read/write.…Hi, I’m Tong Pei, a Master’s student in Artificial Intelligence at Vrije Universiteit Amsterdam with hands-on experience across LLM agent systems, RAG, knowledge graphs, and computer vision. I enjoy turning research insights into practical ML engineering solutions, and I’m currently building agent-centric platforms with public APIs and scalable memory architectures. I’ve designed episodic memory frameworks for multi-agent workflows, optimized LLM retrieval strategies, and reduced hallucinations and token usage in real-world tasks. Previously, I co-founded OmniMemory to deliver an Agent Memory SaaS and contributed to AIoT projects for smart furniture and home devices, including integrations with Xiaomi devices and an OpenClaw memory plugin for autonomous data read/write.

Available to hire

Hi, I’m Tong Pei, a Master’s student in Artificial Intelligence at Vrije Universiteit Amsterdam with hands-on experience across LLM agent systems, RAG, knowledge graphs, and computer vision. I enjoy turning research insights into practical ML engineering solutions, and I’m currently building agent-centric platforms with public APIs and scalable memory architectures.

I’ve designed episodic memory frameworks for multi-agent workflows, optimized LLM retrieval strategies, and reduced hallucinations and token usage in real-world tasks. Previously, I co-founded OmniMemory to deliver an Agent Memory SaaS and contributed to AIoT projects for smart furniture and home devices, including integrations with Xiaomi devices and an OpenClaw memory plugin for autonomous data read/write.

Skills

Experience Level

Expert

Expert

Expert

Expert

Intermediate

Language

Chinese

Fluent

English

Advanced

Work Experience

Co-founder & AI Algorithm Developer at OmniMemory Intelligence Technology (Shenzhen)

November 1, 2025 - May 1, 2026

Led the end-to-end development of an Agent Memory SaaS platform, including public deployment, API encapsulation and remote dynamic memory read/write access for external agent nodes. Designed and implemented LLM-driven agent systems with LangChain, enabling natural-language control and protocol-level integration for Xiaomi smart-home devices and a broad range of cameras. Built task-specific prompt orchestration and workflow pipelines using an in-house Harness framework, reducing hallucination rate by 20% in defined scenarios and improving contextual memory consistency. Developed a memory-system plugin for the OpenClaw framework, enabling automatic account registration and autonomous memory data read/write; improved long-context complex-task memory performance by 40%. Contributed to an AIoT system for smart furniture and developed a patent-pending rail-mounted operating structure for electronic products.

AI Algorithm Engineer Intern at Chengdu Liewei Technology

November 1, 2021 - April 1, 2022

Developed and optimized object detection and facial recognition models using YOLOv3 and U-Net, improving recognition accuracy by 53% compared with the baseline model. Contributed to the full ML development lifecycle, including data collection, cleaning, augmentation, labeling, model training and hyperparameter tuning.