AEGIS
★ 371Runtime policy enforcement for AI agents — cryptographic audit trail, human-in-the-loop approvals, and a kill switch. Zero code changes to adopt.
About
I work on making autonomous AI agents verifiable — so that every tool call, every dollar, and every reasoning step leaves an audit trail you can trust.
I'm a Master's student in Computer Engineering at the University of Southern California, where I research trustworthy and self-evolving agent systems at the Fortis Lab. My work spans agent safety & governance, retrieval and memory hierarchies for long-horizon reasoning, and sim-to-real reinforcement learning for tool use — with a habit of turning each idea into a shipped, open-source system.
Before USC I studied Electrical & Computer Engineering at Shanghai Jiao Tong University. Along the way I've built recommendation models at JD.com, low-latency trading infrastructure at Optiver, and autonomous GEO/SEO agents at Topify.AI. Outside research I'm building Serica, turning global curiosity about China into real trips.
Education
University of Southern California
M.S. in Computer Engineering, Honors Program · Fortis Lab
2025 – 2027Los Angeles, USA
Shanghai Jiao Tong University
B.Eng. in Electrical & Computer Engineering · Minor in Computer Science
2022 – 2026Shanghai, China
HSFZ · CCNU No.1 High School 华中师大一附中
High School Diploma
2019 – 2022Wuhan, China
Open-Source · Flagship
Sovereign-OS
★ 102Constitution-first AI orchestration: one YAML Charter defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP.
Publications
2026 · first-author unless noted. Aojie Yuan highlighted. See Google Scholar for the full list & citations.
10
Do Agent Skills Speak Safety in Every Language? A Cross-Lingual Security Analysis of the Skills Ecosystem
Agent Skills @ ACM CAIS 2026
Experience
Topify.AI Forward Deployed Engineer
Nov 2025 – Jan 2026- Designed & deployed an autonomous GEO/SEO agent system (LangGraph, Inngest, Claude API) orchestrating 6 specialized sub-agents — keyword analyst, content strategist, writer, publisher, visibility monitor, strategy optimizer.
- Built a closed-loop pipeline: the monitor tracks brand share across AI search engines (Perplexity, ChatGPT, Gemini) and feeds visibility deltas back to the optimizer, which dynamically tunes content structure, topic selection & publishing cadence.
- Cut content-ops headcount by 80% and drove 200% revenue growth to $3M ARR, replacing a 5-person team with a single self-optimizing workflow.
LangGraphInngestClaude APIMulti-agent
JD.com Recommendation Algorithm Engineer · Beijing
Dec 2024 – Feb 2025- Helped build an end-to-end generative recommendation framework (semantic-ID retrieval), unifying candidate generation and ranking into one sequence-to-sequence model replacing the multi-stage cascade.
- Used NER to mine 18 key attributes from year-long logs; applied Qwen-VL for item visual-text analysis and Aho-Corasick for efficient query matching, strengthening semantic features and improving codebook utilization for ID quantization.
- Built a multi-view user-behavior module fusing short/long-term interaction sequences via QFormer-based aggregation of hierarchical semantic embeddings from click, order & RSU behaviors.
Generative RecQwen-VLQFormerSemantic ID
Optiver Algorithm Engineer · Shanghai
Dec 2023 – Feb 2024- Developed low-latency components for a volatility-prediction pipeline targeting Chinese commodity futures, supporting automated market-making.
- Accelerated an LSTM volatility model by porting the engine from Python to C++/LibTorch with custom CUDA kernels; achieved a 70% inference-latency reduction (5 ms → 1.5 ms) via TensorRT quantization & kernel fusion.
- Built the real-time market-data ingestion module in C++/ZeroMQ to process tick-level order-book data from Chinese futures exchanges.
C++LibTorchCUDATensorRTZeroMQ
Enjoymi Games 欢动科技 Software Engineer · Shanghai
Aug 2023 – Oct 2023- Maintained core SDKs for two major mobile games — robust login, payment & platform integration.
- Engineered custom SDK integrations for major Android channels (e.g. Xiaomi channel package) and architected a unified authentication interface over the HMS Account SDK, exposing a clean
login()handling silent/explicit sign-in and all auth states.
AndroidJavaHMSSDK
Currently Building
AEGIS
ProductThe runtime safety layer for AI agents — cryptographic audit trail, human-in-the-loop approvals, and a kill switch, adopted with zero code changes. 371★ open-source, live at aegistraces.com.
Sovereign-OS
ProductCharter-governed AI orchestration: a YAML constitution sets mission, budget & rules; CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. 102★ open-source.
Serica
StartupA China-inbound travel platform that turns global curiosity about China into real, bookable trips — AI-generated itineraries, cultural adaptation, and a conversion funnel built for overseas travelers.
BrewNet
StartupAn AI agent that makes professional warm introductions — it reasons over your network and goals to broker curated, high-signal intros to the right people, then handles the outreach end to end.