● Available · Q3 2026 RFour Energy Corp. · ML Consultancy Jakarta · Houston · Remote Est. 2018

Turning subsurface noise
into production signal.

I build machine learning systems and agentic AI workflows for upstream and midstream operators — the kind that survive contact with messy SCADA exports, legacy WITSML feeds, and the engineer who insists everything still lives in a 40-tab Excel file.

Working Stack
Python Agentic AI Excel Dashboards PyTorch LangGraph Power BI Streamlit OSDU PI System
01 / Capabilities

What I actually do.

/ 01

Python & ML Engineering

Production pipelines for forecasting, anomaly detection, and physics-informed models. Built to run on the rig, not just in the notebook.

/ 02

Agentic AI Systems

LLM agents that read daily drilling reports, draft DOIs, and surface non-productive time root causes — with humans firmly in the loop.

/ 03

Excel that scales

Refactoring decade-old reservoir & commercial models into validated, version-controlled tools — without forcing your team off Excel.

/ 04

Operational Dashboards

Power BI, Streamlit, and custom web dashboards wired into PI, OSDU, and SAP — built so a field engineer trusts the number on screen.

02 / Services

Engagements, scoped honestly.

/ 01
ML Discovery Sprint
Two-week engagement: I sit with your subsurface, production, or commercial team, audit the data, and walk out with a prioritized list of ML use cases ranked by ROI and feasibility — plus a working prototype on one of them.
2 weeks · Fixed fee
/ 02
Agentic AI Buildout
Design and ship LLM-powered agents for your operations: DDR summarization, well intervention triage, contract review for offtake agreements, or HSE incident classification. Includes guardrails, evals, and handover.
8–16 weeks · T&M
/ 03
Decision Dashboard
From spreadsheet chaos to one screen your VP of Production refreshes every morning. Built on your existing data warehouse, integrated with PI, OSDU, or SAP. Production-grade, not a demo.
6–10 weeks · Fixed fee
/ 04
Fractional ML Lead
For operators without an in-house ML team: I act as your fractional head of ML — setting strategy, hiring, vendor selection, and architecture review — typically two days a week on a quarterly basis.
Quarterly · Retainer
/ 05
Workshops & Training
Hands-on workshops for petroleum engineers, geoscientists, and reservoir teams — Python from zero, applied ML for subsurface, and how to actually use agentic AI without wrecking your workflow.
2–5 days · On-site or remote
03 / Process

From data to decision.

/ 01

Frame

Sit with the team that owns the decision. Understand the operational pain — not the algorithm someone read about on LinkedIn.

/ 02

Audit

Inventory the data: SCADA, PI, OSDU, drilling reports, the Excel that lives on someone's desktop. Surface what's signal, what's swamp.

/ 03

Prototype

Ship a working model or agent in weeks, not quarters. Tested against historical events you actually remember.

/ 04

Productionize

Wire it into a dashboard, an alerting system, or an Excel-friendly API. Versioning, monitoring, evals — the boring parts.

/ 05

Hand over

Document, train your team, and leave. I'm independent — my goal is to make myself replaceable, not embedded forever.

04 / Selected Work

Numbers worth shipping.

● UPSTREAM 2025
−18%
Non-Productive Time

Drilling NPT prediction for an offshore SE-Asia operator

Trained a sequence model on 6 years of mud-log and rig-state data; deployed as a real-time advisor inside the existing rig dashboard.

● MIDSTREAM 2024
12×
Faster Reporting

Agentic pipeline for daily commercial reporting

LLM agents that pull from SAP, allocation systems, and email attachments to draft a board-ready morning brief — reviewed by a human in 10 minutes.

● UPSTREAM 2024
$4.2M
Annualised Uplift

Production optimization for a 90-well brownfield asset

Per-well choke-setting recommendations from a physics-informed ML model, surfaced in a Streamlit tool the production engineers actually open every shift.

05 / About

Eight years between two industries.

[ PORTRAIT ] ● 35°N 90°W DR. SECRET, ST., MT. 2026

RFour Energy Corp. is a one-desk ML consultancy. The desk belongs to Dr. Secret.

Eight years across two majors and one independent — first as a reservoir engineer in Jakarta and Houston, then leading the data science function for an upstream operator's digital transformation.

RFour Energy Corp. was founded in 2023 because the most interesting ML problems in oil & gas don't sit inside one company — they sit at the seam between the rig, the spreadsheet, and the boardroom. That's where we work.

27 Engagements shipped
14 Operators served
4 Continents worked
/ Q3 2026 · Two slots open

Have a problem worth solving?

pytgoworthed@gmail.com