About · Background · How I Work

I build AI systems that
ship to production.

My work sits at the intersection of applied AI, cloud engineering, and product thinking. I design and build end-to-end AI solutions — from data pipelines and ML models through agent architectures, governance systems, and automated content operations — and I operate them in production at real cost and scale.

Enterprise tech consulting + hands-on AI engineering

My background is in enterprise technology consulting — cloud migration strategy, application rationalization, infrastructure modernization for large-scale organizations. I spent years helping companies answer "what should we do with our technology stack" before AI made that question orders of magnitude more interesting.

Starting in 2024, I went deep on applied AI — not as an observer, but as a builder. Every project in this portfolio represents something I designed, built, deployed, and operated in a real environment against real constraints.

The Park Whisperer — a full-stack AI platform for theme park intelligence — is my personal production system. It runs 24/7 on a stack that spans Azure, GCP, and AWS, processes satellite data from a geostationary orbit, and generates daily AI content published to three social platforms. I built and operate every layer of it alone.

That experience of being the developer, the MLOps engineer, the architect, and the on-call operator simultaneously is what I bring to client work.

How I think about AI systems

⚙️
Production first, prototype second
I design for deployment from day one — not for demos. Every architecture decision is evaluated against operational questions: Who runs it when it breaks? How is it monitored? What does it cost at steady state? What happens when a model call fails?
📊
Quantified decisions
I don't migrate to a new technology without first measuring the cost of the current one. The Data Pipeline Evolution case study documents exactly how I concluded Cosmos DB was adding $394/month with zero benefit — and what the migration back to PostgreSQL cost. Numbers drive decisions.
🔗
Full-stack, not just the model
AI systems are icebergs. The model or agent is the visible 10%. The other 90% is the data pipeline feeding it, the infrastructure running it, the monitoring catching its failures, and the output schema that downstream consumers depend on. I build the whole iceberg.
🛡️
Governance as architecture
For enterprise AI — especially in regulated industries — governance isn't a checkbox after the fact. It's a constraint that shapes the architecture: provenance-by-construction, auditable reasoning chains, human approval gates at the right decision points. I've shipped systems that a compliance officer can review.
💰
Cost discipline
The Park Whisperer platform runs for under $100/month. A 36-application enterprise cloud migration analysis cost $24 in total AI compute. I approach AI cost the same way I approach any engineering trade-off: measure it, understand the levers, and make it an explicit design input.
🔄
Iterate to the right answer
The Ride Whisperer forecasting system went through 8 major versions. The Park Agent went through 3 agent frameworks. Each iteration is documented in this portfolio because the path matters as much as the destination — it shows what failure modes look like and how I work through them.

What I build

Agentic AI Systems
Multi-agent · Tool-use · RAG
Multi-agent pipelines with tool libraries, retrieval-augmented generation over structured and unstructured data, SLM-based intent routing, and multi-model collaboration patterns (cheap model for synthesis, capable model for output). I've built agentic systems on AWS Bedrock, Azure AI Foundry, Azure Functions, and n8n.
Cloud migration intelligence Park Agent Chat Seller Intelligence Knowledge RAG
ML Pipelines & Forecasting
scikit-learn · Prophet · LightGBM · BigQuery
End-to-end ML systems: feature engineering, training pipelines on BigQuery data warehouses, model serialization to GCS, and inference services that serve predictions every 20 minutes. Time-series forecasting for operational systems where latency and cost matter more than marginal accuracy gains.
Weather ML (6 models, 44K obs) Ride Whisperer forecasting Venue impact prediction
AI-Generated IaC & Deployment
Kiro · Bicep · CloudFormation · Terraform
Using AI-powered development tools (Kiro, GitHub Copilot) to generate production-grade infrastructure from specification — Bicep modules, CloudFormation stacks, Cloud Run job definitions, Container App configurations. I've deployed the same application logic to AWS and Azure via AI-generated IaC with zero forked business code.
EARE AWS + Azure Advisory AI AWS + Azure Gov-Process SaaS
Data Engineering & ETL
PostgreSQL · BigQuery · Azure Cosmos DB · pgvector
Real-time data pipelines that run on tight cadences (5–10 minutes), upsert semantics with deduplication, event-driven processing, and warehouse-scale historical data for ML training. Experience across three cloud data platforms and a full cycle of architecture evolution — including the hard lesson of when not to use a NoSQL document store.
Park Data Ingest ETL GOES-18 Lightning Ingestion METAR/Radiosonde pipeline Data Pipeline Evolution
AI Content Operations
Automated content factory · Video · Multi-platform
Scheduled AI pipelines that produce and publish social media content, blog posts, and short-form video with no human touch. ElevenLabs TTS with per-character timestamp alignment, FFmpeg video encoding, word-sync caption generation, and direct API publishing to Instagram, TikTok, and YouTube Shorts.
SLM Content Pipeline AI Video Production Team Multi-Model Content
AI Governance & Compliance
ISO-42001 · NIST AI RMF · SDLC gates
Enterprise AI governance platforms that scan codebases, generate compliance artifacts across 10 regulatory frameworks, and enforce gate-based approval workflows. For clients in regulated industries (healthcare, financial services) where AI deployments require documented provenance and auditable decision chains.
Advisory AI Governance Platform Provenance-by-construction AI Gov-Process SaaS

Stack breadth across the work

Cloud Platforms
Microsoft AzureFunctions · Container Apps · AI Foundry · Cosmos DB
Google Cloud (GCP)BigQuery · Cloud Run · GCS · Cloud Scheduler
Amazon Web ServicesBedrock · Lambda · DynamoDB · CloudFormation
AI / ML
Claude (Anthropic)Sonnet / Haiku · via Bedrock + Azure
OpenAI / GPT-4oEmbeddings · Assistants API · Azure OpenAI
Phi-3 / Phi-4 MiniSLM intent routing · fine-tuning
scikit-learnRandomForest · GradientBoosting · 6 models
LightGBM / ProphetTime-series forecasting
LangChainAgentic loops · tool orchestration
ElevenLabsTTS · timestamp-aligned audio
Data & Storage
PostgreSQL + pgvectorHNSW index · hybrid BM25+vector search
Google BigQueryData warehouse · ML training · ST_DISTANCE
Azure Cosmos DBNoSQL · vector search · Gremlin graph
RedisCaching · pub/sub · session state
Azure Blob / GCSML models · JSON API · video assets
Infrastructure & Deployment
Bicep / ARMAzure IaC — AI-generated via Kiro
CloudFormationAWS IaC — AI-generated via Kiro
TerraformGCP infrastructure · BigQuery · Cloud Run
Docker / Container AppsContainerized jobs · multi-stage builds
GitHub ActionsCI/CD · container build/push · deploy
n8n / CaddyWorkflow orchestration · reverse proxy
Languages & Frameworks
PythonPrimary — ML · pipelines · agents · ETL
TypeScript / Node.jsGovernance platform · SaaS API · Fastify
SQL (BigQuery + PG)Complex views · window functions · spatial
FFmpeg / PillowVideo encoding · image compositing
FastAPICustom microservices · agent backends
Data Sources & APIs
NOAA GOES-18 GLMSatellite lightning · NetCDF · L2 Flash
FAA METAR / aviationweather.govSurface weather obs · 17 stations
NWS / SPC APIsActive alerts · categorical outlook
UWyo Radiosonde ArchiveUpper-air soundings · CAPE/LI/K-Index
ThemeParks.wiki API286 WDW entities · live wait data

Scale across the body of work

24+
Case studies documented
3
Cloud platforms deployed to
44K+
ML training observations
1.6M+
RAG knowledge records
286
Park entities tracked
1,053
Servers analyzed (migration)
Production AI at responsible cost

Every system in this portfolio has a real cost. I track it carefully and treat it as a first-class design constraint.

Cloud Migration Analysis Platform — 36-app enterprise migration analysis (full run)$24 total AI cost
Weather ML pipeline — 17 stations, 20-min prediction cadence~$6/month
Park Whisperer full platform — Azure + GCP + AWS combined<$100/month
Cosmos DB — decommissioned after architecture review$394/mo → $0

What an engagement looks like