███████╗██████╗ ██╗ ██████╗ ███████╗ ██████╗ ██╗ ██╗ ██╔════╝██╔══██╗██║██╔════╝ ╚══███╔╝██╔═══██╗██║ ██║ █████╗ ██████╔╝██║██║ ███╔╝ ██║ ██║██║ ██║ ██╔══╝ ██╔══██╗██║██║ ███╔╝ ██║ ██║██║ ██║ ███████╗██║ ██║██║╚██████╗ ███████╗╚██████╔╝╚██████╔╝ ╚══════╝╚═╝ ╚═╝╚═╝ ╚═════╝ ╚══════╝ ╚═════╝ ╚═════╝
20, waterloo ee. love to run experiments and be proven wrong. building a game theory engine to compute the optimal decision.
Currently
Measuring harnessed cloud agents against Cursor's defaults.
A decision-making engine. Make the right choice, anytime, anywhere.
Claude Code skills
Installable as a plugin. Install once — every skill added later ships to you automatically.
/plugin marketplace add EricJujianZou/skills
Converts corporate AI writing into gen Z slang, preserving meaning. Rizz levels 1–10, from subtle word swaps up to terminal brainrot.
"brainrotify this" · "rizz this up" · "deslopify"
Removes AI-generated text indicators. Targets model leakage, corporate phrasing, and aesthetic tells. Self-critique loops and platform-specific audits.
"humanize this" · "de-AI this" · "remove the AI tells"
Source: github.com/Ericjujianzou/skills
Decision-making engine. Make the right choice, anytime, anywhere.
An agentic software development lifecycle.
Helps non-technical recruiters evaluate candidates from their GitHub code.
Generates and manages reusable LLM prompts.
Won $5,000 at SpurHacks 2025.
Reimplementation, for learning. (repo link pending)
One dashboard for every platform you post to.
- See your live metrics update across all platforms.
- Reuse and re-purpose top-performing content across platforms.
- Automatically edit videos with AI, no extra API tokens needed.
Finds the money you qualify for and writes the applications.
- Automatically sources scholarships, grants, fellowships, internships and programs against your profile, then drafts everything for them.
- Finds the email and LinkedIn of the recruiter for your role.
- Easy onboarding and setup with your AI agent integration.
Education
University of Waterloo
BASc Candidate, Electrical Engineering, Honours · GPA 4.0/4.0
- 2nd, SpurHacks 2025 — $5,000 in funding.
- 1st, Waterloo Engineering Competition, Junior Design.
Experience
Software Engineer · TextNow
- Owned and closed 100+ P1 cross-platform issues across web, Android and backend to GTM-ready quality, while personally shipping 50+ merged PRs across new UX features, flaky-test fixes and bug fixes.
- Automated 200+ hours of unattended code-review responses across 30+ PRs by building a more comprehensive babysitter than Cursor and Anthropic, adopted by another engineering team in 7 days.
- Authored an engineering department-wide agent-native experiment, solving context rot, catastrophic failure and LLM model adaptability problems of fully-autonomous SDLC in production codebases.
- Saved new hires ~5 hours of onboarding time by shipping an Android department-wide onboarding script.
Co-Founder · Anti-Soy
- Interviewed 35 startup founders and recruiters from NVIDIA and Apple to validate the problem, then developed an ML + agentic AI system to help interviewers detect project business need, AI-generated code and bad practices.
- Trained a Random Forest classifier on 14 code-style features (AST parsing and regex) to reach an 86% F1 score detecting AI-generated code, cutting startup hiring cycles by 2 weeks.
- Launched the MVP in 2 weeks and piloting 2 users from Ontario Public Service across 1,500 summer 2026 candidates.
Full-Stack AI Engineer · Revvity
- Spearheaded a biomarker analysis MVP through 4 customer-feedback cycles, pivoting from automated outlier removal to a visual classification system based on user transparency needs.
- Secured a Letter of Intent for a pilot automating 60+ reports across 20+ biomarkers by engineering an ML workflow to process 10+ years of lab data using Python, React, GPT-4o and AWS.
- Architected an LLM-as-a-Judge evaluation pipeline for 60+ agents to address user concerns on LLM transparency, cutting QA costs 7x through multimodal visual sanity checks for 2,000+ end users.
Co-Founder · Articula
- Identified a gap in communication training for immigrant youth by talking to 30+ users, pitched an NLP AI and CV (facial mesh node-tracking) practice tool to VCs and secured $4,100 in pre-seed funding.
- Accepted into Founders University (Launch pre-accelerator) and Microsoft for Startups, managing stakeholder relationships across a 12-week development cycle and receiving $350,000 in cloud credits.
Skills
AI tools
Agent harness, RSI, tmux, sub-agents, vector DB
ML frameworks
scikit-learn, NLP, pandas, TensorFlow, PyTorch
Languages
Python, C++, TypeScript/JavaScript
Cloud & MLOps
AWS, GCP, Postgres, Azure, Docker, Git, SQL, Linux
Delete the scaffold
On @bcherny's approach: delete your system prompt, delete your guardrails, delete your scaffold. Give the agent a task you think is too hard and let it run for days.
The verification loop is the part most people get wrong.
A Pokémon card business card
Built on a 3-hour bus ride. Tilt for holo, tap to flip, full 360 spin opens my Twitter.
Contact
Any of these reach me.