GitHub

English Resume

Hang (Eric) Zheng

Senior Full-Stack Engineer | AI/LLM Systems

Summary

Results-driven Full-Stack Software Engineer with 10 years of experience architecting high-performance distributed systems, Java and Golang backend services, microservices, data platforms, and performance-critical product infrastructure. Over the past two years, I have focused on production-grade AI applications, successfully designing and deploying AI-powered products leveraging AI-agent architecture, LLM orchestration, RAG, tool calling, monitoring, and scalable deployment workflows. I bring a proven track record of end-to-end product delivery, combining robust backend engineering with modern frontend architectures using React, Next.js, and TypeScript.

Professional Experience

Morfeus Technologies Inc. (Delaware, United States)

Senior Fullstack Developer

2025-09 - Present

AI market intelligence platform for FX and macro trading.

  • Designed and developed Morfeus, an AI/LLM-powered market intelligence platform for FX and macro trading, spanning conversational research, War Room risk monitoring, data feeds, session recaps, and Trade Lab workflows.
  • Architected a neural orchestrator that aggregated and validated outputs from 33 AI agents to produce consensus-backed views on currency pairs, macro events, and trade ideas.
  • Integrated Polygon, Event Registry, Myfxbook, COT, and structured internal research datasets to power agent reasoning, market regime classification, news sentiment analysis, and research workflows.
  • Delivered production-grade product infrastructure across Next.js, React, TypeScript, FastAPI, Python, Redis, Supabase/Postgres, OpenAI, Stripe, background workers, PDF reporting, testing, and CI/CD.

Cheetah Mobile (Joyme)

Fullstack Developer (Java/Golang)

2020-08 - 2024-12

Overseas Live Streaming

  • Led the design, development, and maintenance of the LiveMe risk control platform using Golang, Kafka, and Elasticsearch.
  • Refactored core modules from Java to Go, improving task scheduling efficiency and reducing resource consumption.
  • Introduced real-time event streaming with Kafka and user profiling in Elasticsearch, achieving second-level risk decision responses and reducing server costs by 30%.
  • Built and maintained a data warehouse on AWS Redshift, integrating multiple risk sources for unified analytics and reporting.
  • Developed a streaming data ingestion platform capturing MySQL Binlog to Kafka and persisting data to Amazon S3, Hive, and analytics systems, processing over 10TB daily.
  • Implemented a high-performance data service platform using Netty and Spring Boot, handling 40 million daily calls with flexible query modes.
  • Created a Sqoop-JDBC plugin to support sharded table ingestion into Hive, streamlining daily ETL workflows.

Quant Group

Java Backend Developer

2017-02 - 2020-08

Internet Finance

  • Contributed to the development and maintenance of the credit wallet backend system using Spring Boot, MyBatis, Hibernate, MySQL, Redis, and RabbitMQ, supporting over 100K DAU and peaking at 1M daily.
  • Led the redesign of loan fund management and repayment modules, implementing circuit breakers, automated allocations, and streamlining third-party integration strategies for financing partners.
  • Simplified integration processes for new lenders, reducing onboarding time and enhancing system maintainability.
  • Received the Annual Best Employee award and monthly Culture Star award for outstanding technical leadership and team collaboration.

Cybercloud Company Beijing

Software Engineer

2016-05 - 2017-02

Cloud Gaming Platform

  • Led development of user, product, and session management modules during a full rewrite of a legacy cloud gaming business system.
  • Helped deploy a nationwide system with daily page views over 100 million and reduced database concurrent reads from over 500/s to approximately 30/s on non-peak days.
  • Built a Flume to Kafka to JStorm to MongoDB/HDFS log analysis pipeline processing over 1 TB per day.
  • Resolved high CPU usage and thread-safety issues in KafkaSpout and fixed offset skew; the system ran stably for more than 6 months.

Other Projects

Software Developer

2015-06 - 2016-05

  • Central Hospital Appointment and Call Platform.

Selected Technical Projects

Neural Orchestrator Research System

Next.js / TypeScript / FastAPI / OpenAI

  • Built a multi-agent orchestration layer that merged outputs from 33 AI agents into consensus-backed research for currency pairs, macro events, and trade ideas.
  • Used consensus validation, signal ranking, and LLM-driven synthesis to support higher-confidence market reads instead of a single-model chat flow.

War Room and Data Feed Workbench

Redis / Supabase / Postgres / Polygon / Event Registry / Myfxbook

  • Built a risk dashboard that combined agent signals into risk-on and risk-off states, risk scores, priorities, and real-time monitoring views.
  • Integrated live prices, retail sentiment, COT positioning, currency strength, seasonality, and news sentiment into a unified trading research surface.

Trade Lab and Product Infrastructure

Stripe / PDF reporting / Workers / CI/CD

  • Implemented session recaps, PDF report generation, trade journaling, performance tracking, and strategy review workflows.
  • Delivered product-grade capabilities including authentication, subscriptions, trial flows, payment handling, user permissions, background workers, and automated testing.

Joyme Risk Control Platform

Golang / Kafka / Redshift / Elasticsearch

  • Rewrote core Java modules in Golang to address high latency and resource consumption in scheduled tasks.
  • Introduced Kafka for real-time event streaming, reducing risk decision response time to seconds.

Streaming Data Ingestion Platform

Java / Kafka / Amazon S3

  • Supported MySQL binlog capture to Kafka and data landing to Amazon S3, MySQL, and Sensors Data platform.
  • Served streaming compute tasks and business database synchronization to Hive/Sensors, handling over 10 TB of data per day.

Data Service Platform

Netty / Spring Boot / MySQL

  • Handled approximately 40 million daily calls, about 462 calls per second.
  • Supported multiple data sources including Elasticsearch, MySQL, and Hive with flexible query modes.

Education

Monash University

Master of Information Technology, Information Technology

2025-07 - 2026-12

Beijing Jiaotong University

Bachelor of Science, Computer Science and Technology

2022-03 - 2024-06

China University of Geosciences (Beijing)

Associate Degree, Computer Application Technology

2019-09 - 2020-12

Skills

  • Multi-agent Systems
  • LLM Orchestration
  • RAG
  • Tool Calling
  • Prompt Engineering
  • OpenAI
  • Claude
  • Gemini
  • LangChain
  • LlamaIndex
  • Semantic Kernel
  • Pinecone
  • Weaviate
  • Qdrant
  • ChromaDB
  • Java
  • Golang
  • High-concurrency Distributed Systems
  • Spring
  • Spring Boot
  • Microservices Architecture
  • Netty
  • Redis
  • Kafka
  • MySQL Index Optimization & Transactions
  • FastAPI
  • Next.js
  • React

Open Source Projects

Baiye-RPC

A Java-based RPC scheduling framework built on Netty and CGLIB for efficient remote procedure calls.

Baiye-Task

A distributed scheduled task framework in Java with master/slave mode, dynamic JAR loading, and reflection.

baiye-framework

A lightweight Java framework that mimics Spring, featuring an IOC container and AOP support via CGLIB.

SMZDM_Monitor

A Python scraper for SMZDM with keyword-based monitoring and email/WeChat notifications.

BaiyeJVM

A Go implementation of a Java Virtual Machine based on the "Write Your Own Java Virtual Machine" book.

Achievements & Languages

  • Bachelor of Science in Computer Science and Technology - Beijing Jiaotong University (2024)
  • Annual Best Employee - Quant Group
  • Monthly Culture Star - Quant Group
  • English: IELTS 6.5
  • Mandarin: Native