AI Research Collaboration CCHIA

Certified Mentor SNU Engineering CORFO Semilla

Jorge Carpanetti

AI/ML Engineer and Director of Strategic Alliances at Cámara Chilena de Inteligencia Artificial. I build software-defined assets for industrial plants using asynchronous checklist data — bridging ML engineering with strategic energy policy. B.E. Energy Resources Engineering, Seoul National University.

7+ years bridging engineering & data

5 languages · 4 countries

$50M+ bilateral investment facilitated

Selected Work

FluidOps SCADA
React 19 · TypeScript · Vite 8 · Tailwind 4
WebSocket OPC-UA · Recharts · ml-spectra
Railway · Vercel

FluidOps SCADA

open_in_new

Real-time digital twin for industrial water pumps. OPC-UA telemetry over WebSocket, MAD noise analysis, Q-P cross-correlation, 6-state pump state machine, 8-threshold alarm system, auto-tagged regime classification.

#React#WebSockets#SCADA#DigitalTwin

Pump Test Bench (RPi)
FastAPI · Python · SQLite · Docker ARM64
Affinity Law Simulation · OPC-UA Bridge
GPIO Hardware Abstraction · systemd

Pump Test Bench

Raspberry Pi backend with synthetic hydraulic telemetry (affinity laws), electrical signature simulation (inrush, harmonics), OPC-UA bridge protocol. REST API, WebSocket dual broadcast, Docker ARM64 with systemd auto-start.

#Python#RaspberryPi#Docker#OPC-UA

gavel

Economic Affairs · Korea Embassy

Facilitated $50M+ in bilateral investment between Korean and Chilean energy/mining sectors. Commercial due diligence, macroeconomic reporting, strategic liaison with Ministries of Energy and Mining. Represented Korea in Pacific Alliance energy dialogues.

#IntlRelations#EnergyPolicy#MarketIntel

visibility

Computer Vision R&D · Incheon

I+D project with Incheon Municipality (South Korea) developing computer vision models for anomaly detection in childcare facilities. Applied ML to high-impact social use case. Conducted at TG Consulting Seoul.

#ComputerVision#AnomalyDetection#R&D

Technical Stack

AI / ML

scikit-learn Random Forest ml-spectra AutoML Causal Inference Deep Learning Computer Vision

Frontend

React 19 TypeScript Vite 8 Tailwind 4 Recharts

Backend

FastAPI Python 3.10+ SQLite WebSockets OPC-UA Pandas

Infrastructure

Vercel Cloudflare Workers Railway Docker Raspberry Pi GCP

Leiden ↔ Chile Seminar

calendar_month

July 27–31, 2026 Sala B05 · Beauchef 851 · FCFM · Universidad de Chile

Attending

DAY 1 · MON 27

AM AutoML & OpenML van Rijn

OpenML task-based metalearning enables zero-shot pipeline selection for unseen pump variants. TabPFN handles tabular classification with missing values — directly applicable to checklist data.

Q: Does TabPFN preserve sensor-channel relationships across multi-variant families?
→ van Rijn suggested per-variant fine-tuning heads.

PM Causal Discovery Salehkaleybar

FCI and RFCI algorithms for constraint-based causal discovery under latent confounders. Conditional independence tests on maintenance logs can identify operator-driven confounding in unobserved shift assignments.

Q: How to distinguish common-cause from direct causation in DAGs from periodic oil-analysis logs?
→ Agreed to discuss further.

NOTE Strong alignment: AutoML gives the how (pipeline generalisation), causal inference gives the why (intervention effectiveness). Both sessions converge on the same open problem — sparse, irregular industrial data.

TUE 28

Optimization · Fan

Multi-objective maintenance routing with stochastic travel times.

TUE 28

Quantum · Laarman

#SAT model counting for pump controller verification.

WED 29

Fairness · Saxena

Structural bias in operator-asset maintenance networks.

Open Research Questions

psychology

FOR VAN RIJN

One Pipeline for 50 Pump Variants

"Can meta-learning generalise anomaly detection across pump families from sparse, low-frequency shift logs? How does TabPFN handle industrial tabular data with mixed numerical/categorical fields and missing entries — without per-variant labels?"

account_tree

FOR SALEHKALEYBAR

Causal Graphs from Maintenance Logs

"How to build causal DAGs from partial maintenance observations with latent confounders (operator experience, shift conditions, ambient temperature)? Can counterfactual reasoning estimate the true effect of maintenance interventions on MTBF from periodic, non-continuous logs?"