Applied AI Engineering · Python Backends · Enterprise Integrations
Irvine, California · Deloitte

I build AI applications that connect models, business workflows, and enterprise systems. My work spans backend architecture, hands-on implementation, conversational prototypes, and evaluation across customer support, healthcare, and public-sector services.

I care about clear interfaces, observable behavior, and useful products people can trust.

LinkedIn · X · ClawHub

• AI application backends: Python APIs, retrieval and generation, agent orchestration, and enterprise integrations.
• Reliability and evaluation: explicit lifecycle states, typed responses, failure handling, and testable model outputs.
• Practical AI tools: agent skills, monitoring, workflow automation, and community software.

Client engagements are described by industry; client names and internal project identifiers are omitted.

• AI-powered customer support — backend ownership and technical coordination. Owned the design and development of a Python/Flask case-assistance backend connecting Salesforce Service Cloud with Vertex AI/Gemini and Discovery Engine. Led backend architecture decisions and coordinated onshore and offshore contributors across API contracts, authentication, error handling, telemetry, and integration dependencies.
• Conversational AI for healthcare — solution design and prototyping. Designed and prototyped pharmaceutical-service workflows for case creation, interaction summaries, and human handoff using conversational agents, Python callbacks, structured JSON, and controlled mocks. Defined lifecycle rules and acceptance criteria that distinguish request acceptance from confirmed case creation and summary persistence.
• AI tools for public-sector services — implementation, evaluation, and maintenance. Enhanced document-processing components with Spanish and Arabic form variants and precision/recall/F1 evaluation. Built an initial backend API for analyst productivity tools with typed responses and timeout handling, and maintained a policy assistant's Docker, Python, and dependency components.

I build skills and infrastructure in the OpenClaw ecosystem, with an emphasis on explicit scope, visibility, and human control.

Published on clawhub.ai/JonathanJing:

• skill-trust-auditor — Security audit for ClawHub skills. Static analysis + LLM-as-judge with 4-layer prompt injection defense. Advisory-only: the LLM never affects the trust score.
• rag-eval — RAG evaluation toolkit built on the Ragas framework. Automated quality scoring for retrieval-augmented generation pipelines.
• openclaw-gateway-watchdog — Out-of-band gateway monitoring. Dual-layer: LaunchAgent + cron. Alerts even when OpenClaw is down. (GitHub)
• openclaw-dashboard — Analytics dashboard. Cache-aware cost estimation, mobile PWA, cookie auth. (GitHub)
• openclaw-tally — "Tokens tell you how much you paid. Tasks tell you what you got." Task-level efficiency analytics. (GitHub)
• glass2claw — Vision Router for smart glasses → Discord → Notion. Instruction-only workflow design.

Tech lead for Grace Irvine Church's digital infrastructure (volunteer):

• ProPresenter-Automation-Agent — AI agent that automates worship presentation workflows in ProPresenter
• Ministry-Scheduler — Automated scheduling for ministry teams
• Ministry-data-visualizer — Data visualization dashboard for church ministry metrics
• Ministry-Clean — Data cleaning pipeline for ministry records
• WorshipFlow — Worship service planning and automation
• AI-sermon-workflow — AI-assisted sermon preparation workflow
• catechism-cards — Interactive catechism study cards

• Asynchronous-FIFO — Async FIFO in Verilog
• Stock-Trading-Strategy — Quantitative trading strategy with backtesting
• Web2Ebook — Scrape web content and convert to ebook format
• Hermes-handbag — Data analysis of Hermès handbag resale market

Stack: Python · TypeScript · RAG · LangChain · Ragas · GCP (Vertex AI, Document AI) · AWS (SageMaker) · Docker · Spark/Databricks

Certs: AWS ML Specialty · Databricks GenAI Engineer · Microsoft Power BI