From design to implementation
Hands-on development experience grounds my architecture decisions in what teams can build, maintain, and improve.
A LITTLE INTRODUCTION
A curious
mind.
A builder’s
heart.
I’m Vicky, an AI engineer and solution architect with 17+ years of enterprise product experience. I help teams solve business problems with practical software, automation, and AI — from understanding the need to delivering the solution.
ALWAYS CURIOUSEST. HUMAN
Ideas into action.
Build. Learn. Make it better.
01 / THE PERSONEXPERIENCE, CURIOSITY, AND PRACTICAL JUDGMENT.
HELLO, I’M VICKY GUO.
I like the space
between “what if”
and “it works.”
17+ yearsCross-industry experienceEnd-to-end delivery
I bring more than 17 years of enterprise product experience across consumer e-commerce, enterprise SaaS, and AI-powered healthcare. My experience spans software development, architecture design, and product ownership, giving me an end-to-end perspective on both business needs and technical delivery.
I understand the problem, explore multiple approaches, and weigh their trade-offs to design practical, reliable solutions. From product direction and system architecture to implementation and ongoing improvement, I connect the pieces to deliver the right solution for the problem.
Vicky.BUILDER BY PRACTICE.
LEARNER BY NATURE.
LEARNER BY NATURE.
EXPERIENCE THAT CONNECTS THE PIECES
An end-to-end perspective.
See the whole system
I compare approaches against business needs, integration requirements, cost, and reliability to choose a practical path forward.
Connect delivery to purpose
Product ownership brings user needs and priorities into technical decisions, from defining the problem to shaping the solution.
17+ years across consumer e-commerce, enterprise SaaS, and AI-powered healthcare.
02 / SELECTED WORKHOW I CHOOSE AND BUILD.
Selected work.
Personal projects and proofs of concept, each with the reasoning behind it.
Config-driven ML pipeline
A reusable machine-learning pipeline on Airflow, MLflow, FastAPI, and Docker. Adding a dataset takes a new config folder, not new code — three demo pipelines (hospital readmissions, gene expression, energy load forecasting) run on the same codebase.
Judgment call: in a hospital-readmission forecasting experiment, I investigated a feature that reflected past readmission performance, removed it to test the remaining predictors, and documented the lower score and the limits of the model.
- Airflow
- MLflow
- FastAPI
- Docker
- CI
Workflow automation & testing with Prefect
Uses Prefect orchestration to automate API-level and end-to-end integration testing of data workflows, with scheduled and automation-triggered worker pools running in containers.
Why it matters: a lightweight, flexible pipeline keeps data reliable for analysis and ML/AI work — because better AI starts with better data.
- Prefect
- Python
- Containers
RAG technique reference
Twelve working retrieval-augmented generation techniques — from naive RAG to Self-RAG, Graph RAG, and RAPTOR — each built in both LangChain and LlamaIndex, run on a local LLM, and scored with RAGAS.
Why it matters: choosing a RAG design means comparing trade-offs side by side, not defaulting to one pattern.
- LangChain
- LlamaIndex
- ChromaDB
- RAGAS
- Local LLM
View code ↗Based on NirDiamant/RAG_Techniques
LLM & RAG evaluation, compared
Evaluates the same LLM and RAG systems with DeepEval, MLflow, and Ragas on local models, then maps which framework fits which job.
Why it matters: AI output should be measured, not assumed — and the right evaluation tool depends on the question.
- DeepEval
- MLflow
- Ragas
- Ollama
- LM Studio
03 / WHAT I DOIDEAS INTO SOMETHING USEFUL.
Curiosity, applied.
From the right question to the right solution.
01Understand the problemPROBLEM FRAMING
Start with the people, goals, and constraints. Clarify what needs to change and what success looks like before choosing the technology.
02Compare the approachesSOLUTION ARCHITECTURE
Explore multiple solutions and make their trade-offs clear — including complexity, cost, reliability, and room to grow. Choose the approach that best fits the specific problem.
03Deliver end to endENGINEERING & DELIVERY
Connect software, data, and AI where they add value. Take the solution from architecture and implementation through evaluation, deployment, and ongoing improvement.
WORK WITH MEPRACTICAL HELP, FROM IDEA TO DELIVERY.
A problem to solve?
Let’s work on it.
AI where it adds value. Automation where it makes sense. Start with the outcome your team needs.
Workflow automation
Find repetitive work, connect systems, and design dependable workflows.
Start with: a workflow review and a prioritized automation plan.
AI feasibility & evaluation
Assess where AI fits and how to measure whether a proposed solution is useful and reliable.
Start with: a focused use-case assessment and evaluation plan.
Architecture & delivery
Compare technical options and turn a product idea into an implementation plan, prototype, or application.
Start with: an architecture review and an agreed delivery scope.
Discuss a project
Tell me the problem, the outcome you want, and your constraints.
04 / NEXT CAREER PATHEXPERIENCE MEETS WHAT’S NEXT.
OPEN TO THE RIGHT OPPORTUNITY
Real problems.
The right solutions.
AI where it adds value. Automation where it makes sense. I bring an end-to-end perspective to choosing and delivering the solution that best fits the problem.
I’m looking for AI Engineer & Solution Architect roles, where I can help teams turn real business problems into useful, reliable AI products.
With 17+ years across software development, architecture, and product ownership, I connect business needs with technical delivery. I want to help teams choose the right approach, build reliable data and AI workflows, and take solutions from an early idea into production.
05 / BEYOND THE SCREENTHERE’S MORE TO THE STORY.
GROWTH WITH PURPOSE
Always learning.
Living with purpose.
I set goals that give life meaning — and work toward them with curiosity, discipline, and consistent practice. There’s always something new to learn and another level to pursue.
Lifelong learning
Ask me about something I don’t know today, and tomorrow I’ll be learning it and trying it hands-on. Curiosity becomes progress through practice.
Tennis
A self-taught 3.5+ level player, consistently working toward a higher level. Every practice is a chance to refine my skills and raise my game.
Taekwondo
Eight years of disciplined training and a third-degree black belt. A practice built on commitment, solid fundamentals, and steady growth.
LET’S CONNECT