EXPERIENCE / RUIZHANG ZHOU

Applied AI / AI Platform Engineer

KI:connect AI Platform

RWTH IT Center | Software Engineer (AI Platform) | Sep 2024 - Present

I contribute to a multi-tenant platform that gives users and applications access to LLMs through a web interface and APIs. My work spans provider behavior, request and response handling, metering, integration reviews, and service diagnostics.

Core Stack
C#/.NET ASP.NET Core OpenAI-compatible APIs Vue 3 MongoDB SignalR
Protocol & Provider Integration
Metering & Governance
Agent Tools & RAG Integration
Operations & Reliability
Links

KI:connect

TalkEcho

Actively developed personal fork | TypeScript · Tauri · Rust

A desktop meeting-caption and dictation application using configurable speech-to-text and LLM providers. My contributions focus on making live workflows more reliable and usable.

GitHub Repository (fork of Pluely)

LLM Gateway

Independent open-source project | Python

A task-aware model router for personal automation jobs. Applications request a task type, while routing policy chooses from the available models.

GitHub Repository

Additional API testing experiment: CompatBench.

Time Series Generative Models for Traffic Scenario Generation

RWTH Cyber-Physical Mobility Group | Master Thesis | Oct 2023 - Apr 2024

Tech Stack
Python PyTorch TimeGAN Diffusion-TS NVIDIA H100 CUDA NumPy Pandas
Challenge

Implement and train time series generative models to synthesize realistic vehicle trajectory data for autonomous vehicle testing. Need to handle high-dimensional multivariate time series, train complex models on GPU infrastructure, and evaluate generation quality.

Solution

The thesis connects ML model development with the data processing and evaluation needed to study generated trajectories.

Links

GitHub Repository | Thesis PDF

LLM & GNN Research for Medical Image Analysis

RWTH Chair of DBIS | Research Assistant | Jul 2023 - Mar 2024 (9 months)

Tech Stack
Python PyTorch Transformers LLaMA Ollama BLIP PyG CUDA GPU Cluster
Challenge

Explore chest X-ray report generation by combining vision and language models in a research setting.

Solution

This research experience introduced me to model serving, multimodal pipelines, and GPU-based experimentation.