Portrait of Arky Yang
Open to AI-first teams πŸ“ Fremont, CA

Arky Yang

Core engineer at Atlassian building an enterprise-scale context platform for AI agents β€” end to end, from zero to release.

In a large enterprise, context is scattered across 10,000+ repos. AI made writing code in any one repo fast β€” so the bottleneck moved to cross-service context understanding and coordination. We build the engine that closes that gap β€” a small team of ~10 engineers that moves faster than any other: deep cross-repo code search, where an organization's business logic actually lives, fused with docs and other sources into the comprehensive context an agent needs to act.

Now
πŸ— Context platform for AI agents Β· Atlassian Rovo Dev πŸ›  Rederive Β· a "Roblox for education" platform (building) 🐻 Cedartale Β· voice-cloned AI storytelling (shipped)
01 β€” Summary

The engineer who holds both sides of the agent boundary

I built an enterprise context engine for AI agents and took it from zero to external release β€” the thing an external-facing AI chat product and external customer launches now run on, and the SDLC agent products our company is building will rely on it, too. I worked as the connective engineer across 10+ partner teams to turn diverse business needs into one coherent, agent-facing platform. On the side I build Rederive and Cedartale, which keeps me sharp on both the agent-side ergonomics and the production-system constraints β€” at the same time.

End‑to‑end Owned the context engine β€” itself an agent, backed by powerful cross-repo code search β€” across API, auth, ops & UI
10+ teams Partner teams coordinated for one external onboarding journey
Zero β†’ External From zero to external release, powering live customer launches
Agent-first MCP-exposed platform + CLI agent full-context mode
02 β€” Selected Work

Software Engineer, Code Intelligence

🧭

Context retrieval agent

Designed and built the orchestrator agent that, given a user query, plans and executes the right sequence of search / explore / file calls to assemble the context downstream AI features consume.

πŸ”

Cross-repo code search at scale

Designed the public API contract β€” versioning, errors, pagination, permission semantics, MCP-friendliness β€” that every agent, service, and external customer integrates against, exposed via MCP and a CLI agent's full-context mode. Reworked the querying and indexing pipeline to be pluggable across search providers and ranking algorithms, so quality and speed can keep improving behind a stable interface.

🌐

External tenant & host onboarding

Took code search from one source host to multi-host (one third-party host launched, another in progress). Coordinated 10+ partner teams β€” source control, provisioning, billing, edge gateway, AI product β€” into a working end-to-end onboarding journey for external customers, including GitHub repo index onboarding.

πŸ”

Permission & auth across hosts

Multi-tenant permission resolution, account-ID-to-tenant mapping for third-party code, and a governed service-to-service onboarding contract so downstream callers integrate through a documented process rather than ad hoc.

βš™οΈ

Production & operational readiness

Multi-tier rate-limit policy (per-client Γ— per-user Γ— per-operation) distinguishing humans, internal bots, external clients, eval traffic, and load tests, plus a generous edge-gateway ceiling. Experience-id propagation for traffic attribution, an integrator troubleshooting runbook, and trace-first debugging for "why did the agent get nothing?" failures.

πŸ–₯️

Code search & chat frontend

Built and shipped the user-facing surfaces for code search and the AI chat experiences that consume it (React/TypeScript) β€” so the same context engine powers both programmatic agents and end-user product flows.

πŸš€

Raised the team's AI leverage

Found and integrated the tools that multiply our team's agent workflow (on Rovodev, Atlassian's coding agent) by orders of magnitude: a Splunk MCP for agent-led debugging, a Slack integration that auto-answers and resolves support-channel questions, and a shared Confluence doc registry any agent can pick up to load full context on a highly complex project.

03 β€” Side Projects

Both sides of the agent boundary

πŸ›  In progress Β· unreleased

Rederive

A "Roblox for education" platform with an agent harness for creation.

Anyone with an AI agent can author courses in their domain, and a Socratic teaching agent (also built by me) guides learners through them. The authoring side is a BYO-agent pipeline β€” fully autonomous (YOLO) or human-in-the-loop β€” that goes from one prompt to a fully animated, narrated video or interactive course.

  • Autonomous long-horizon execution
  • BYO-agent contracts β€” a packaged plugin bundling skills + MCP
  • Zero-to-one creative pipelines
  • The pedagogy & UX of a teaching agent

Same problem shape as agent-coding harnesses β€” applied to education.

🐻 Shipped

Cedartale

Voice-cloned AI storytelling app for kids.

A parent's own voice can read the story. Founder, sole engineer, sole product designer β€” the whole loop from idea to a shipped consumer app, including user research. In 3 weeks.

  • User research with parents & kids
  • Self-deployed voice-cloning & caption-alignment models
  • One-click picture-book generation with theme & style consistency
  • Consumer product, end to end

Founder Β· sole engineer Β· sole product designer.

04 β€” Stack

What I use day to day

Backend

Kotlin / SpringPythonGo RedisPostgresGraphQLOpenSearch RailwayModal

Infra & platform

Edge / API gatewayService-to-service auth User authEvent-streaming Container deploy pipelines

AI

Claude CodeRovodev CLI CursorWindsurf OpenClaw + GLMMCPs & skills

Observability

Distributed tracingProduction log platforms SplunkSignalFxTime-series dashboards

Frontend

ReactTypeScript Admin & portal UIs
05 β€” Education & before

Chemistry, then computer science

MS, Computer ScienceUT Austin
2020–2022 Β· GPA 4.0
Chemistry, Resnick FellowCaltech
2016–2020 Β· GPA 3.9
BS, Chemistry (Highest Honors)UC Berkeley
2014–2016 Β· GPA 3.95
ChemistryHKUST
2011–2013 Β· GPA 3.79
Visiting Student, Organic ChemistryUC Santa Barbara
2014

CS coursework: Android, deep learning, computer vision, optimization, front-end. Pre-CS research: 2D organic–inorganic hybrid perovskite materials for optoelectronics (Harry Atwater Group, Caltech), copper nanowire synthesis for transparent electrodes (Peidong Yang Group, UCB), polymer solar cells (He Yan Group, HKUST). Publications include Giant Enhancement of Photoluminescence Emission in WS2–Two-Dimensional Perovskite Heterostructures.

Earlier β€” SWE Intern (2021)

  • React/TypeScript + Jest reusable card UI components for distributed services.
  • Event-driven Spring Boot/Kotlin/GraphQL backend for default-component provisioning on site creation.
  • In-product help search experiments (Algolia, React Context & Hooks) with content design.

Outside engineering (it shows up in the work)

  • President, Caltech Entrepreneurship Club (2017–2020) β€” alumni-CEO panels, the FLOW/Rockey Fund program for young tech companies, Idealab field trips.
  • Plug and Play (2019) β€” analysed pitch presentations across verticals.
  • Calibr at Scripps Research (2018) β€” research & market landscape of new depression meds.
  • Mom of a two-year-old β€” an excellent forcing function for thinking carefully about AI.