Kurt Brischke

Deriva Energy · Brookfield Renewable · Charlotte, NC

Systems builder across three industries: family ERP in Nicaragua, architect of a 4.5+ GW Databricks Lakehouse at Brookfield Renewable, product owner on Lighthouse at Duke Energy, and an independent 13-advisor AI operating system. 15+ years inside the asset, not pitching to it. Where AI work today needs judgment, design, and first-principles ownership more than raw engineering horsepower, I span all four: code, AI leverage, business, and hardware.

Save Contact View Portfolio

By the Numbers

$20M+
Realized Portfolio Impact Across AI & Analytics Initiatives
2.5B
Rows Across 180+ Tables · Held to Data-Quality Standards for 8+ Years
1.6M
Sensors Streaming Every 10 Min Across 4.5+ GW Fleet
Patent
Co-Inventor, Descriptive Analytics (SMART)
EPRI
Award for Innovation in Renewable Analytics
6 + 15+
Data Scientists Product-Owned (Lighthouse) · AI Initiatives Led as Brookfield AI Champion

Production AI Systems I've Built

End-to-end data products, not demos. Each one goes from data source through pipeline to intelligent decision surface. The same pattern I apply at 4.5+ GW industrial scale, shipped solo.

Scout AI Concierge
Multi-tenant AI concierge platform for wellness studios. Designed multi-tenant from Day 1 (KSH is tenant #1). Text-based booking, member coaching, churn prevention, rate limiting, Airtable integration. Production pattern: data pipeline → LLM judgment → customer-facing decision surface.
Node.js Claude API TypeScript Multi-Tenant SaaS
Investor Intelligence Suite
Dual-thesis portfolio monitoring with an automated 7-evaluator alert engine. 15-minute data pipeline, morning and evening briefs, macro tracking, earnings analysis. Real-time decision intelligence on a 14-table PostgreSQL schema.
Next.js 16 Python Pipeline PostgreSQL 14-Table Schema
Health Command Center
Personal health operating system with 42-expert tiered framework. Apple Health auto-sync, sleep analytics, biomarker tracking, workout programming across 22 routes. Full-stack from sensor data → expert framework → interactive dashboard.
Next.js 16 React 19 PostgreSQL Apple Health API

Independent AI Infrastructure

01
Semantic Memory MCP Server. Supabase (PostgreSQL + pgvector) with Voyage embeddings, hybrid semantic + full-text search via Reciprocal Rank Fusion. 26 tools, 4,400+ memories. Same Lakehouse pattern (ingest → embed → retrieve) applied to a personal data estate.
02
Autonomous Agent Fleet. 27+ scheduled agents running daily and weekly intelligence: inbox triage, opportunity scouting, portfolio monitoring, health analysis. Each with its own prompt engineering, context window, and success metric.
03
13-Advisor AI System. Specialized agent personas for career, finance, health, strategy, and technical architecture. Model assignment, cross-advisor escalation rules, and shared knowledge vault.
04
Agentic Skill Framework. Modular skill system for automated document generation (PDF, DOCX, XLSX, PPTX), research workflows, and orchestration. Judgment-as-code.
05
Voice Pipeline. Apple Watch speech-to-text via Bonjour with HMAC auth, routed to Claude Code for hands-free interaction. Edge → cloud → agent.

Foundations First / How I Ship

AI is the multiplier. The four layers below are what it multiplies. Each one extends what the layer beneath it makes possible. Get them right and AI compounds across the business. Skip them and AI-first collapses on first contact with reality.

Business Operations DNA
IT Systems + Data Discipline
Product Judgment + Design
AI Products That Ship

Most candidates have one or two layers. The compounding shows up when all four sit on top of each other. The four principles below are how I work that compounding in practice.

01
First principles over status quo. Every system I touch, whether a 3,000-person ERP in Nicaragua, a 4.5+ GW Lakehouse, or a personal agent fleet, starts from the physics of the problem and the shape of the data, not the latest model or the existing tooling.
02
Judgment and design are the durable jobs. When 1 to 2 engineers plus AI compound to what used to take 15, the bottleneck shifts to product ownership, scoping, and knowing what not to build. I product-owned 6 data scientists on Lighthouse at Duke. Now I ship solo at similar velocity.
03
Data sensitivity is a feature, not a burden. What moves, what stays, who sees it. Two years as enterprise Data Steward and migrating 1.6M individual sensors off-prem taught me the calls AI-first companies are about to face at scale.
04
Real-world constraints drive architecture. SCADA latency, 300-foot tower climbs, control-logic timing, sensor drift. The hardware teaches you what clean abstractions cannot. Most generalist AI candidates have never touched a physical system. It shows in the decisions they miss.

Enterprise Experience

Manager, Performance Analytics · AI Infrastructure Leadership
Deriva Energy (Brookfield Renewable) · 2021 – Present
  • Databricks Lakehouse Architect. Architect of the Lakehouse design and deployment. Delta Lake, Unity Catalog, Medallion Architecture, streaming pipelines (10-minute micro-batch). Consolidated petabytes from 80+ renewable sites across 4.5+ GW (1.6M individual sensors). $20M+ in realized portfolio impact across initiatives.
  • Chilton Manual for Wind Turbines. COO-sponsored LLM diagnostic copilot mapping SCADA faults to resolution data across 90+ OEM manuals. 85% join fidelity. Projected $3.6M to $5.0M per year steady-state. Led architecture POC validation with IT, operations, and data-science stakeholders before full build.
  • Production ML at Scale. Directed multi-year McKinsey collaboration deploying 22 component-level failure forecasting models. Reduced unplanned downtime 18 to 25%. Prevented 3+ catastrophic failures ($1.5M+ each).
  • Product Owner across 3 agile teams (data science, analytics engineering, operations). 12 to 15 person cross-functional org. Product-owned 6 data scientists on Lighthouse analytics modernization at Duke.
  • Brookfield AI Champion. Leading 14+ AI use cases at Deriva within Brookfield's 15-portfolio-company, 7-country AI Value Creation Office. Driving toward the $10M 2026 AI value target.
  • $7.1M saved through LTSA compliance and vendor LD recovery (2021–2026). Led vendor POC validation and negotiated multi-year platform contracts with Seeq and Onyx.
Previous: Duke Energy Renewables, American Apparel (Director of Capacity Planning), Ashley Furniture, Pinehurst Manufacturing
15+ years across renewable energy, manufacturing, retail · 6 years US + Nicaragua (bilingual) · Microsoft Professional Degree in Data Science

Speaking & Recognition

EPRI Award. Innovation in Renewable Analytics.
Patent Co-Inventor. SMART (Solar Monitoring and Reliability Tool).
Brookfield AI Summit. Inverter PdM with AWS (Toronto, 2025).
Seeq Conference Presenter. Bat Curtailment Analytics.
McKinsey Collaboration. Multi-year ML engagement for turbine failure forecasting.
Education. MBA (UNC Charlotte) · B.S. Mgmt & Acct (USC, Full Scholarship) · Studied abroad: Italy, Spain
LLM Architecture RAG Systems Agentic AI Claude API / MCP Databricks Delta Lake / Unity Catalog AWS SCADA / PI Python + SQL Vector Embeddings Power BI Product Ownership Predictive Maintenance Data Governance Executive Translation Spanish (Proficient)

Get in Touch

Save Contact Download Resume