中文版

About me

Hi, I’m Jason Wang, a Sydney-based software engineer focused on agent systems and infrastructure. I’m currently a Member of Technical Staff at Lingopal. Previously, I was a tutor at the University of Sydney’s School of Computer Science.

I’m the lead maintainer of NoKV, an open-source infrastructure project providing persistent workspaces and state management for AI agents. NoKV is part of the Linux Foundation ecosystem, listed in both the LF AI & Data and CNCF landscapes, and is also catalogued in CMU’s Database of Databases (DBDB.io) by Prof. Andy Pavlo. NoKV is actively collaborating with LoopX (5.8K+ GitHub stars), OpenViking (37K+ stars), and Hermes Agent (245K+ stars).

I’ve been building with generative AI since late 2023 and have helped two local startups develop customer-facing AI agent systems from scratch. At THDR Group, I implemented the core agent workflow for Neuono, an AI fashion platform later featured in Forbes Australia and showcased at New York Fashion Week in September 2025.

My capstone project, EchoJournal, is essentially a very early, independent prototype of the ChatGPT Dot concept: a voice-native personal memory system powered by a real-time voice model. It was selected for the University of Sydney’s Genesis Accelerator, Cohort 36, in late 2025.

I value the combination of product development and infrastructure engineering in practical AI applications, particularly in industries beyond tech. I’m especially interested in working closely with domain experts to understand their workflows and turn their needs into useful, reliable agent systems.

Fun fact: I was a journalist back in 2019.

Experience

  1. Present
  2. Present

    LoopX

    Maintainer

    Designed shared-goal state and execution ownership for long-running agents. Fenced claims, idempotent writeback and restart-safe recovery give agents and hosts one durable authority while keeping runtimes and storage replaceable.

    5.8K GitHub stars (as of 2026-09-13).

  3. Present

    NoKV

    Co-founder & Lead Maintainer

    Lead engineering, downstream use-case discovery and open-source collaboration alongside my day job. Evolved a Go distributed filesystem into a Rust workspace and persistent state layer for agents, and opened AI-for-science pilots alongside atomate2/jobflow.

    Listed in the CNCF and LF AI & Data Landscapes. The early Go version is catalogued by CMU DBDB.io.

  4. to

    Genesis Accelerator

    Cohort 36

    Built EchoJournal as a very early, independent prototype of the ChatGPT Dot concept: a voice-native personal memory system with searchable transcripts, daily-to-monthly reflections and a WebRTC voice agent. Users can revisit and reflect on their past journal entries through real-time voice conversations with the agent.

    University of Sydney Genesis Accelerator, cohort 36.

  5. to

    The University of Sydney

    Tutor & Teaching Assistant

    Taught object-oriented programming, software construction and design, testing, and databases across five undergraduate units. Delivered 14 teaching hours each week, helping students reason about debugging and architectural trade-offs.
  6. to

    PicSEO AI

    Full-stack Engineer (Contract)

    Independently built and shipped v1.0 of an image management and sharing system for photographers. Owned chunked uploads, isolated storage, encrypted sharing, metadata, real-time rendering and billing.

    100+ daily active users and 30+ paying users in the first month.

  7. to

    Neuono

    AI Software Development Engineer (Contract)

    Built the data and retrieval architecture and core fashion design-to-order agent workflow from scratch. Designed the production-database-to-Graph-RAG ETL and graph model, grounding personalised product previews in authoritative garment metadata and images before translating approved designs into order-ready specifications.

    Showcased at New York Fashion Week 25SS.

Education

The University of Sydney

Master of Computer Science

-

Newcastle University, UK

MA, International Multimedia Journalism

-

Skills

Languages
Rust, Go, Python, TypeScript / JavaScript, SQL
Systems
Distributed storage, Raft, MVCC, WAL / checkpoints, persistent ART, S3, Linux I/O, Docker, Kubernetes
Applied AI
Agent orchestration, Graph RAG, provenance, real-time voice / WebRTC, vLLM / SGLang, inference scheduling and KV-cache lifecycles

Writing