Software Engineer | Generative AI | Full-Stack Systems

Edison Xu

Building AI products, web applications, and AI agent systems end-to-end.

Georgia Tech MS CSEHighmark Health · Generative AIU.S. work authorizedOpen to remote / relocation

About

I build production-grade AI products people actually use.

A software engineer focused on generative AI, full-stack product development, and intelligent systems.

I'm Edison, a software engineer building AI-powered products at the intersection of full-stack engineering, retrieval, and agent systems.

At Highmark Health, I've worked on real-time AI training platforms, planner–executor–critic multi-agent research workflows, and document intelligence tools on top of Vertex AI Search. My focus is designing systems where LLMs, retrieval, and infrastructure work together to produce grounded, auditable, and reliable behavior in production.

Based in

Atlanta, GA, USA

Work preference

Open to remote roles and relocation · U.S. work authorized

Current focus

AI products, agent workflows, retrieval systems, and production engineering

How I work

Product-minded, highly ownership-driven, and comfortable shipping end-to-end

Looking for

Software engineering roles focused on AI products, intelligent workflows, and user-facing platforms

Background

Experience and education

The work I’ve done, the systems I’ve owned, and the foundation behind how I build.

Highmark Health

Software Engineer (Generative AI team)

Full-time

Feb 2025 - Present

Built production-grade internal AI systems spanning real-time interaction, multi-agent research, and enterprise retrieval workflows. Shipped a real-time call-center training platform, a citation-backed Planner–Executor–Critic deep research system, and an enterprise document Q&A workspace using grounded retrieval, reranking, and Vertex AI Search—while contributing to CI/CD, Cloud Run deployments, and observability for reliability at scale.

Real-time AIMulti-Agent SystemsRetrieval / RAGVertex AI SearchCloud RunCI/CD

Highmark Health

Software Engineer Intern (Generative AI team)

Internship

May 2024 - Dec 2024

Contributed to core AI platform and retrieval capabilities across internal tools, model integrations, and source-grounded workflows. Built a multi-modal platform on Vertex AI, a RAG-based policy assistant for grounded summarization, and a centralized Gemini proxy service—while improving reliability with Pytest coverage above 90%.

Vertex AIRetrieval / RAGGemini APIAI PlatformPolicy Q&ATesting

Education

Academic foundation

Master of Science in Computational Science & Engineering

Georgia Institute of Technology · 2022-2024

Graduated December 2024

Bachelor of Arts in Applied Economics

University of California - Santa Barbara · 2019-2021

Graduated March 2021

What I bring

Highlights

End-to-end ownership across product, backend, and applied AI workflows

Experience taking AI ideas from prototype to production-ready systems

Strong focus on retrieval, multi AI agent systems, and real-world usability

Product-minded engineering approach focused on reliability, clarity, and adoption

Projects

Selected work

A few representative projects across AI systems, distributed backend work, and product-facing engineering.

AI/Plugin Development · 2025

FigBrain: Figma Multi-Agent Plugin

Built a Figma AI agent at the Microsoft AI Hackathon, enabling natural-language prompts to generate and populate FigJam components via the Model Context Protocol (MCP) and automated Figma API/plugin flows. Designed a supervisor multi-agent system using LangGraph, where a master orchestrator routed tasks to planner, executor, and verifier agents with Chain-of-Thought prompts and ReAct loops, validated at ~85% first-try accuracy. Cut API costs ~28% and lowered latency through long/short-term memory mechanism, plan/result caching, and dynamic model switching between lightweight and advanced LLMs.

Tech stack

Figma APILangGraphMulti-Agent SystemsModel Context ProtocolChain-of-ThoughtReAct Loops

Backend Development · 2024

Golang-based High-Efficiency Search Engine

Developed a Go-based search engine with text and vector search capabilities, using gRPC for microservices architecture. Implemented a distributed web crawler with Kafka cluster integration for efficient data collection and processing. Enhanced search relevance using TF-IDF and BM25 ranking algorithms, with Trie trees for optimized query suggestions.

Tech stack

GogRPCKafkaTF-IDFBM25Trie TreesMicroservicesDistributed Systems

Full-stack Development · 2023

CloudBin: Cloud-Based Distributed File Storage System

Designed a storage system using Spring Boot, Vue3 and AWS S3, featuring chunk-based file uploads for reliability. Leveraged Redis with a Bloom Filter to prevent cache penetration, boosting cache hit rate and reducing database load. Integrated ElasticSearch for efficient fuzzy file name searches, reducing search time and improving accuracy.

Tech stack

Spring BootVue3AWS S3RedisBloom FilterElasticSearchChunk-based Uploads

Capabilities

Broad enough to ship, focused enough to specialize.

I care less about listing every tool and more about showing the systems and outcomes I can reliably deliver.

Capability

AI product systems

AI Product Systems

LLM-powered products, retrieval workflows, and orchestration patterns designed for grounded outputs, reliable behavior, and production use.

Best at

Retrieval / RAGMulti-agent workflowsLLM application architectureEvaluation & iteration

Commonly use

Vertex AI
Gemini API
LangGraph
Embedding models
Search / reranking

Capability

Product execution

Full-Stack Product Engineering

User-facing product development across frontend, backend, and the details that make systems feel clear, polished, and easy to use.

Best at

React / TypeScriptPython / Go servicesSystem architectureAPI design & implementation

Commonly use

Next.js
Vue.js
REST APIs
State management
Design systems

Capability

Platform reliability

Backend, Cloud & Reliability

APIs, infrastructure, deployment, and data foundations built to be observable, scalable, and production-ready.

Best at

Service architectureAPI designDeployment pipelinesObservability

Commonly use

Docker
Kubernetes
GCP / Cloud Run
Redis
SQL / PostgreSQL

Capability

How I work

Engineering Approach

I move quickly, communicate clearly, and care about building systems that are technically sound, useful to users, and maintainable over time.

Best at

End-to-end ownershipProduct thinkingFast iterationClear communication

Commonly use

Cross-functional collaboration
Structured problem solving
Pragmatic decision-making
Learning agility

Let's connect

Interested in AI systems, product engineering, or a team that ships ambitious work well?

I'm always happy to talk about thoughtful engineering, product-minded AI work, and the kinds of technical challenges that benefit from both system design and user empathy.

Direct

edisonapply@gmail.com 626-552-1696

@EdisonWhale

Social

LinkedIn GitHub

Email me View resume

Software Engineer | Generative AI | Full-Stack Systems

Edison Xu

Building AI products, web applications, and AI agent systems end-to-end.

Georgia Tech MS CSEHighmark Health · Generative AIU.S. work authorizedOpen to remote / relocation

About

I build production-grade AI products people actually use.

A software engineer focused on generative AI, full-stack product development, and intelligent systems.

I'm Edison, a software engineer building AI-powered products at the intersection of full-stack engineering, retrieval, and agent systems.

Based in

Atlanta, GA, USA

Work preference

Open to remote roles and relocation · U.S. work authorized

Current focus

AI products, agent workflows, retrieval systems, and production engineering

How I work

Product-minded, highly ownership-driven, and comfortable shipping end-to-end

Looking for

Software engineering roles focused on AI products, intelligent workflows, and user-facing platforms

Background

Experience and education

The work I’ve done, the systems I’ve owned, and the foundation behind how I build.

Highmark Health

Software Engineer (Generative AI team)

Full-time

Feb 2025 - Present

Real-time AIMulti-Agent SystemsRetrieval / RAGVertex AI SearchCloud RunCI/CD

Highmark Health

Software Engineer Intern (Generative AI team)

Internship

May 2024 - Dec 2024

Vertex AIRetrieval / RAGGemini APIAI PlatformPolicy Q&ATesting

Education

Academic foundation

Master of Science in Computational Science & Engineering

Georgia Institute of Technology · 2022-2024

Graduated December 2024

Bachelor of Arts in Applied Economics

University of California - Santa Barbara · 2019-2021

Graduated March 2021

What I bring

Highlights

End-to-end ownership across product, backend, and applied AI workflows

Experience taking AI ideas from prototype to production-ready systems

Strong focus on retrieval, multi AI agent systems, and real-world usability

Product-minded engineering approach focused on reliability, clarity, and adoption

Projects

Selected work

A few representative projects across AI systems, distributed backend work, and product-facing engineering.

AI/Plugin Development · 2025

FigBrain: Figma Multi-Agent Plugin

Tech stack

Figma APILangGraphMulti-Agent SystemsModel Context ProtocolChain-of-ThoughtReAct Loops

Backend Development · 2024

Golang-based High-Efficiency Search Engine

Tech stack

GogRPCKafkaTF-IDFBM25Trie TreesMicroservicesDistributed Systems

Full-stack Development · 2023

CloudBin: Cloud-Based Distributed File Storage System

Tech stack

Spring BootVue3AWS S3RedisBloom FilterElasticSearchChunk-based Uploads

Capabilities

Broad enough to ship, focused enough to specialize.

I care less about listing every tool and more about showing the systems and outcomes I can reliably deliver.

Capability

AI product systems

AI Product Systems

LLM-powered products, retrieval workflows, and orchestration patterns designed for grounded outputs, reliable behavior, and production use.

Best at

Retrieval / RAGMulti-agent workflowsLLM application architectureEvaluation & iteration

Commonly use

Vertex AI
Gemini API
LangGraph
Embedding models
Search / reranking

Capability

Product execution

Full-Stack Product Engineering

User-facing product development across frontend, backend, and the details that make systems feel clear, polished, and easy to use.

Best at

React / TypeScriptPython / Go servicesSystem architectureAPI design & implementation

Commonly use

Next.js
Vue.js
REST APIs
State management
Design systems

Capability

Platform reliability

Backend, Cloud & Reliability

APIs, infrastructure, deployment, and data foundations built to be observable, scalable, and production-ready.

Best at

Service architectureAPI designDeployment pipelinesObservability

Commonly use

Docker
Kubernetes
GCP / Cloud Run
Redis
SQL / PostgreSQL

Capability

How I work

Engineering Approach

I move quickly, communicate clearly, and care about building systems that are technically sound, useful to users, and maintainable over time.

Best at

End-to-end ownershipProduct thinkingFast iterationClear communication

Commonly use

Cross-functional collaboration
Structured problem solving
Pragmatic decision-making
Learning agility

Let's connect

Interested in AI systems, product engineering, or a team that ships ambitious work well?

I'm always happy to talk about thoughtful engineering, product-minded AI work, and the kinds of technical challenges that benefit from both system design and user empathy.

Direct

edisonapply@gmail.com 626-552-1696

@EdisonWhale

Social

LinkedIn GitHub

Email me View resume