18 years enterprise operations → AI systems

Justin Erwin

AI Product Manager & Technical Builder

I spent 18 years in large-scale hospitality operations across multiple Las Vegas properties, most recently as Executive Director with full P&L responsibility for a $200M+ business. Then I moved into product to build the tools I always wished existed on the floor. Today I design AI systems for complex workflows, real operational constraints, and measurable business outcomes.

View workContactLinkedIn
Reztrix · system snapshot
Grounded AI for frontline execution
298+ REST endpoints across 33 routers
69 public tables with 339 RLS policies
50 synthetic scenarios. 84% pass rate, up from 42% baseline
FastAPIpgvectorLLM-as-JudgeSSEHITL
298+
endpoints
69
tables
42→84%
eval pass rate
01Proof Strip

Operational Scale. Product Impact.

20%
INBOUND CALL VOLUME REDUCTION

Operational lead on an AI guest support assistant deployment at a $200M+ Las Vegas resort. Ran pre-launch testing cycles, frontline team comms, and rollout enablement across Guest Services, PBX, and Concierge. Launch drove a 20% reduction in inbound call volume.

42% to 84%
EVAL PASS RATE

Built a custom LLM-as-judge framework across 50 synthetic scenarios, improving pass rate from 42% to 84% through iterative root-cause analysis.

52→64
NPS LIFT IN ONE YEAR

Built Power BI dashboards with custom DAX measures that powered a loyalty-tier personalization program at a $200M+ Las Vegas resort. Targeted room assignment, amenity timing, and service workflows by loyalty segment drove a 12-point NPS lift in one year.

15→32%
MOBILE CHECK-IN ADOPTION

Owned end-to-end product delivery for a mobile check-in rollout across multiple Las Vegas properties (9,000+ rooms): user journey mapping, functional requirements, vendor coordination, and frontline enablement. Adoption more than doubled in the rollout window.

02Tier 1 · Live Flagships

Three projects I'd show you first.

AI OPERATIONS PLATFORM · SYSTEM PROTOTYPE
Reztrix: Frontline Ops Intelligence

AI decision-support system for frontline operations in complex physical environments. Built to connect scattered property workflows with safer AI-assisted action, including evaluation pipelines, fallback logic, and human approval where the cost of error is high.

FastAPIpgvectorRAGHuman-in-the-Loop
DATA PRODUCT · LIVE TOOL
BurgReport: Fine Wine Pricing Intelligence

Live pricing intelligence tool for fine wine. Aggregates scattered market data via Claude API web search, normalizes it through a Python FastAPI backend, and serves benchmark views in under three seconds.

FastAPIClaude APISupabaseRailway
KNOWLEDGE SYSTEM · LIVE PROTOTYPE
Spatial Limen: Structural Inference Engine

Evidence-grounded structural inference system for comparing complex information while preserving provenance, uncertainty, and reviewer control. Designed to surface deeper relationships beyond standard search or chatbot interfaces.

Next.jsThree.jspgvectorProvenance
03Tier 2 · Enterprise Strategy

Product strategy for regulated workflows.

PRODUCT STRATEGY · RESEARCH ARTIFACT
Regulated Transfer Exception Workflow

Research-backed product strategy for AI-assisted fraud review, structured evidence assembly, and audit trails in regulated financial transfers. Designed around strict timing constraints, human-in-the-loop review, and institution-controlled decisions.

ACATSEvidence WorkflowAudit TrailHITL
04Technical Credibility

The stack I actually use.

MODELS & EVALS
Claude SonnetLLM-as-JudgeSynthetic scenariosStructured output
RETRIEVAL & GROUNDING
RAGpgvectorPolicy embeddingsSupabase
BACKEND & DATA
PythonFastAPIPostgreSQLREST APIs
INFRASTRUCTURE & SECURITY
RLS policiesEdge Functionspg_cronSSE streamingHuman-in-the-loop
EDUCATION & CREDENTIALS
MBA, Kelley School of BusinessStanford GenAIAWS Certified AI PractitionerAWS Certified Cloud PractitionerPSPO I

Contact

Senior PM and PM roles in AI-forward SaaS and hospitality tech. Remote US or Las Vegas.

Email JustinLinkedIn