Xiang Yashan

Software Engineering · Big Data

Long-standing focus on consumer electronicsA solid sense of visual aestheticsAbility to learn and iterate quicklySkilled at evolving intelligent enterprise processesCommitted to optimizing human-computer interaction

Undergraduate rank: 2/59; undergraduate GPA: 4.02/5.0; English proficiency: CET-4 (556), CET-6 (451). Overall skills: During my internship at Rayneo, I designed and built an intelligent knowledge-base system fusing LLMs with Milvus, along with an Agent-based AIOps platform that delivers intelligent, closed-loop operations. At SAP, I shipped a production-grade CAP application that streamlined the data-to-print business flow and achieved a 30%+ efficiency gain. At Bosch, I designed a multimodal document intelligence-processing system and drove the platformization and unified deployment of algorithms. I have a strong command of technology stacks such as Python and PyTorch, with capabilities in Agent development, knowledge-base construction, RAG-based Q&A, and model fine-tuning, and I excel at identifying business pain points and designing AI solutions.

Skills

LLM & Agent
LLMAgentAIOps
RAG & Knowledge Base
RAGMilvusLangflow
Python & PyTorch
PythonPyTorch
CAP & Node.js
Node.jsCAPSAP BTP
Deep Learning & Signal
Deep LearningSignal ProcessingRF
AR & Unity
UnitySwiftHoloLensAR
Tech Timeline
2021 – 2024RF Vital-Sign Signals & Deep Learning
PythonDeep LearningRF
2024AR 3D Authoring & LLMs
SwiftUnityARLLM
2025LLM Agents & Knowledge Bases
PythonLLMAgent
2025Enterprise Cloud-Native Applications
Node.jsBTPCAP

Experience

Rayneo, Shenzhen
Rayneo, Shenzhen
Algorithm / AI Engineering Intern
2025.09 – Present
  • Built the core of an intelligent knowledge base: designed and implemented an intelligent customer-service knowledge-base system fusing LLMs with Milvus, covering semantic search, CRUD, version management, and RAG-based Q&A, providing AI-driven knowledge retrieval and decision support for platform support and community operations.
  • Built a closed-loop intelligent operations system: created an Agent-based AIOps service that automatically collects logs for Wi-Fi/Bluetooth connection anomalies and performs full-chain analysis. It generates solutions for known issues and escalates unknown ones to the technical team, achieving intelligent, traceable, closed-loop operations.
RayneoMilvusAgent
SAP Labs China, Shanghai
SAP Labs China, Shanghai
Cloud-Native Application Development Intern
2025.06 – 2025.09
  • Shipped a production-grade application: designed and implemented the development and deployment of a cloud-native CAP application on the SAP BTP platform, automating the enterprise data-transformation and printing workflow. Responsible for service-interface design and deployment monitoring, running stably in production with a 30%+ improvement in process efficiency.
  • Accumulated enterprise-grade development experience: gained hands-on mastery of Node.js application and LLM integration development, delving into business processes and designing efficiency-boosting solutions leveraging AI tooling. The project spanned the complete pipeline from requirements analysis to deployment monitoring, delivering solutions for enterprise AI digital transformation.
SAPNode.jsCAP
BSH Home Appliances, Nanjing
BSH Home Appliances, Nanjing
AI Algorithm Development Intern
2025.03 – 2025.06
  • Designed and built multimodal document intelligence processing: for diverse document types such as recipe data and interaction reports, designed and developed an LLM-Agent-based automated processing pipeline delivering information extraction, tag generation, content summarization, and more, achieving an 80%+ recall rate.
  • Drove the platformization of AI algorithms: developed the StreamPilot production solution on Langflow, designing multiple reusable processing components that enable drag-and-drop algorithm reuse across scenarios, turning technical solutions from code into configurable platform services.
B/S/HLangflowAgent

Education

Nanjing University
Nanjing University
MSc · Recommended Admission / School of Software · Software Engineering
2024 – 2026
Recommended for postgraduate admission to Software Engineering, School of Software, Nanjing UniversityResearch focus: Human-Computer Interaction
Research Project

State Key Lab for Novel Software Technology · NJU — Terrain3DSketch

2024.06 – Present

Research on accelerating 3D authoring and modeling on AR platforms. Responsible for the deep-learning generative algorithms and terrain data processing, and developed the Unity/HoloLens-based Terrain3DSketch system, which lets users sketch mid-air and automatically generates controllable, personalized terrain models.

VR/ARDeep Learning3D Authoring
Nanjing University of Posts and Telecommunications
Nanjing University of Posts and Telecommunications
Bachelor / College of Computer Science · Data Science and Big Data Technology
2020 – 2024
Undergraduate major rank: 2/59Undergraduate GPA: 4.02/5.0English proficiency: CET-4 (556) · CET-6 (451)
Research Project

Jiangsu Provincial Key Lab of Wireless Sensor Networks · NJUPT — RF Non-Contact Vital-Sign Monitoring

2021.01 – 2024.06

As principal investigator, completed a provincial-level Undergraduate Innovation project: an RF-based non-contact intelligent vital-sign monitoring system, which earned an Outstanding completion evaluation. My undergraduate thesis, built on this work, was named a Jiangsu Provincial Outstanding Thesis. Responsible for the deep-learning core algorithms and signal-data acquisition and processing, and built a complete non-contact heartbeat-detection system with the Streamlit visualization frontend, reaching 93.05% heart-rate computation accuracy at low latency.

Deep LearningSignal Processing

Research

"A Method for Estimating Human Heart Rate Based on Radio-Frequency Signals"
First inventor; patent granted. Co-filed 10+ patents within the group during undergraduate studies.
National Invention Patent ZL 202310056016.3
"MAE-based self-supervised pre-training algorithm for heart rate estimation of radar signals"
First author; published.
SCI Q3 · Sensors (IF 3.9)
"Heart rate estimation algorithm for radar signals based on wavelet threshold noise reduction and Resnet50"
First author; published.
EI · 35th Chinese Control and Decision Conference (CCDC 2023)
"Terrain3DSketch: Freehand Mid-air Sketching for Terrain Generation"
Fourth author; under review.
IEEE VR 2025 (CCF-A)

Awards

Provincial Third Prize, Computer Design Competition

Awarded as team leader.

Far East Education Scholarship

Awarded by the Far East Holding Group.

Professional Skill Certificates

ATA AutoCAD Application (Mechanical) Intermediate certification; Jiangsu Computer Rank Exam Level-2 C Programming (Distinction); National Computer Rank Exam Level-2 C Programming certificate.