Agent 01Code
Build, test, and ship.
Cloud Automation · AI Infrastructure · Agent Systems
Frank Zhang
Building reliable platforms for AI systems. I bring cloud automation, observability, testing, and recovery principles to agent infrastructure and developer workflows.
Cloud automationCloud environments, automation, and operational tooling.
Agent systemsReasoning, orchestration, memory, and tool use.
AI infrastructureDeployment, monitoring, and recovery for AI workloads.
Scroll to explore
02 / EVOLUTION
From infrastructure
to agent systems.
My experience covers systems support, infrastructure, cloud engineering and automation. I now apply that background to agent systems.
Engineering focus: repeatable workflows, monitoring, and operational controls.
2017Systemssupport and operations
2018Infrastructureoperations and procedures
2019Cloudcloud hosting and engineering
2020 →Automationcloud platform, Kubernetes and GCP
NowAI SystemsAgents · memory · LLMOps
03 / ORCHESTRATE
Agent
orchestration.
I work on agent workflows for planning, research, coding and automation, with task delegation, monitoring and human review.
Agent Orchestrationplan · delegate · observe · improve
Agent 02Research
Read, compare, extract signal.
Agent 03Experiment
Run experiments and review results.
Agent 04Observe
Watch systems and surface drift.
Agent 05Automate
Automate repeatable tasks.
Human layerCuriosity
Choose the task and review the result.
04 / FEATURED PROJECT
Agent
Memory Bridge.
AMB stores explicit project decisions for later recall, with their sources and revision history.
- 01 / DecideRecord the decision and its reason.Record a reviewed decision with its context and source.
- 02 / CheckRecall selectively.On a later task, relevance, revisions, and governance shape what is returned.
- 03 / ContinueCheck against current evidence.Use selected memory as a starting point, then check it against live evidence.
Conceptual workflow · not a live activity feed or automatic record of every session.
05 / SELECTED SYSTEMS
Selected
engineering work.
Cloud automation, agent infrastructure and research tooling. The entries below describe the work, methods and available sources.
Developer systems
Automation & platform engineering
Cloud automation and platform engineering on GCP: Kubernetes (GKE), Argo Workflows, Python and CI/CD, with provisioning and maintenance run as automated workflows.
Context
- Work
- Built and operated automation around cloud infrastructure and developer workflows.
- Tools
- GCP, Kubernetes (GKE), Argo Workflows, Python and CI/CD.
Featured engineering system
Agent infrastructureAgent Memory Bridge
A local-first memory system for explicit project decisions, selective recall, provenance and revisions across agent sessions.
System evidence
- Problem
- Project decisions and their reasons can become scattered across coding sessions.
- System
- AMB stores explicit decisions for later recall, with provenance and revision boundaries.
- Boundary
- Durable decisions stay distinct from current repository facts; AMB is not an automatic transcript archive.
- Evidence
- The public repository documents runnable evaluation checks and their limits; these are not broad productivity results.
Sources: AMB documentation; evaluation scope.
Open-source integration
Agent Memory Skills
Companion skills for connecting agent hosts to AMB and using explicit, governed project memory.
Context
- Focus
- Host capability discovery and governed memory workflows.
- Approach
- Separate host connection and tool discovery from everyday recall and memory decisions.
06 / EXPERIENCE
Engineering
experience.
My roles have covered systems support, infrastructure, cloud hosting, automation and platform engineering.
2020 — now
Cloud automation and platform engineering
Kubernetes (GKE) and Argo Workflows on GCP: provisioning and maintenance run as automated workflows, plus automation for infrastructure and developer workflows. Tools: GCP, Kubernetes (GKE), Argo Workflows, Python, CI/CD.
2019 — 2020
Cloud engineering
Cloud hosting and engineering, after earlier infrastructure and operations internships.
2017 — 2018
Infrastructure and systems internships
Systems support, infrastructure operations, cloud operations and release work.
07 / BUILDING BLOCKS
Tools
and methods.
Cloud infrastructure
GCP, Kubernetes, deployments and cloud operations.
Platforms & runtime
Developer and agent environments, runtime state and failure handling.
Automation
Workflow automation with checkpoints, tests, monitoring and rollback.
Evaluation & observability
Checks for correctness, drift, context quality, latency, cost and failure modes.
08 / CONNECT
Get in touch
about a project.
I am a senior cloud automation engineer in the Greater Toronto Area. My interests include AI infrastructure, agent systems and developer platforms.
Emailsend message
GitHubcode & projects ↗
LinkedInexperience ↗
Back to topreturn to top ↑
Frank ZhangGreater Toronto Area · Cloud Automation / AI Infrastructure / Agent Systems