Available for collaboration

Blaude

AI Infrastructure Engineer

I build distributed intelligence systems, healthcare data platforms, and production AI automation tools. Status at a glance, depth on demand.

46
CPU Cores
58
GPU Cores
64
NPU Cores
168GB
Unified Memory
blake@engine-room ~ %
$tlm scan --cluster --verbose
ENGINE ROOM CLUSTER SCAN • 4 NODES DETECTED
ALPHAONLINE
ModelM4 Pro Mini
CPU14-core @ 4.5GHz
GPU20-core
Memory64GB Unified
Compute~17.5 TFLOPS
DELTAINCOMING
ModelM4 Pro Mini
CPU14-core @ 4.5GHz
GPU20-core
Memory64GB Unified
Compute~17.5 TFLOPS
BRAVOONLINE
ModelM4 MacBook Air
CPU10-core @ 4.4GHz
GPU10-core
Memory24GB Unified
Compute~15.4 TFLOPS
GAMMAONLINE
ModelM1 Mac Mini
CPU8-core @ 3.2GHz
GPU8-core
Memory16GB Unified
Compute~13.6 TFLOPS
NODES
4
CPU CORES
46
GPU CORES
58
MEMORY
168GB
TFLOPS
60+
✓ Cluster scan complete • 3 nodes online, 1 incoming • Total: 60.0 TFLOPS
View ProjectsGet in Touch
TypeScriptPythonSwiftPostgreSQLFastAPINext.jsSwiftUI

By the Numbers

Real production systems, real code, real infrastructure

3,109
Git Commits
Across 11 active repositories
1.31M
Lines of Code
Swift, TypeScript, Python, SQL
48TB
Total Storage
8TB internal + 40TB RAID 0
60+
TFLOPS
4-node Apple Silicon cluster
168GB
Unified Memory
168
Total Cores (CPU+GPU+NPU)
4
Production Nodes

Featured Projects

Production systems built to solve real problems at scale

"Status at a glance, depth on demand" — Every system answers "is everything OK?" in one second. NASA mission control aesthetic: calm authority, warm displays, zero clutter.

Lantern Medicare

Healthcare Pricing Intelligence

Production healthcare pricing engine powering 30.9 million precomputed Medicare rates. Complete coverage of 413 metropolitan areas across 6 years (2021-2026). Sub-second pricing for 10,000+ CPT codes.

30.9M
Price Records
413
Markets
<100ms
Query Time
PostgreSQLFastAPISwiftUIPython

Telemetry

Distributed Intelligence Dashboard

Full-stack monitoring system for ENGINE ROOM cluster. Real-time metrics across 4 nodes, 46 CPU cores, 58 GPU cores, 64 NPU cores, and 168GB unified memory. Cross-platform (Web + iOS + iPadOS) with secure remote access via Cloudflare tunnels.

46
CPU Cores
58
GPU Cores
64
NPU Cores
168GB
Total RAM
1s
Refresh Rate
ReactFastAPISwiftUICloudflare

Murmur

Voice Conversation Intelligence

Native iOS voice intelligence system. Voice-activated recording with real-time speaker identification, live transcription via Apple SFSpeechRecognizer, and Claude AI conversation analysis. Built with AVAudioEngine + SwiftData for local-first conversation storage.

Live
Transcription
Multi
Speaker ID
40%
Complete
SwiftSwiftUISwiftDataClaude

ENGINE ROOM

4-Node Apple Silicon Cluster

Distributed AI inference cluster delivering ~60 TFLOPS combined compute. Two M4 Pro Minis (ALPHA + DELTA), M4 MacBook Air (BRAVO), and M1 Mini (GAMMA) running Ollama + EXO for local LLM inference. Auto-routing, load balancing, $200-400/month API cost savings.

46
CPU Cores
58
GPU Cores
64
NPU Cores
168GB
Memory
60+
TFLOPS
OllamaEXOPostgreSQLLlama

Bloom

Daily Wellness & Life Goals

Full-stack wellness app with dual-layer tracking (daily habits + monthly goals). FastAPI + Supabase backend, native SwiftUI iOS app. Claude-powered insights detect patterns and correlations. Couples mode with shared accountability.

2-Layer
Tracking System
AI
Pattern Insights
<30s
Daily Check-in
FastAPISupabaseSwiftUIClaude

OpenClaw Control

AI Infrastructure Management

Native iOS/iPadOS control center for OpenClaw AI infrastructure. Manage sessions, agents, and deployments from your device. Real-time cron job monitoring, model switching, and node health checks. Built for power users who need full control on the go.

Native
iOS/iPadOS
Remote
Control
Live
Monitoring
SwiftUIWebSocketREST API

Get in Touch

Have a project in mind? Let's talk about building something powerful together.