Senior Platform Engineer · vacancy
Here's what AI can do for this role — and what still needs a human. Built straight from ENSEK's own job advert, running live on my_db.ensek_demo.accounts — 27,640,145 real rows via MotherDuck (DuckDB). Not a slide about AI. The job, getting done.
Every line on the left is lifted from ENSEK's actual job ad. If a card lacks a harvested JD line, it is omitted. On the right is the AI doing it — with eligible cards running live against the warehouse and offline inspection clearly labelled in the workspace.
“Understand internal developer needs and platform strategy, using insights to drive technical decisions.”
How is the platform load distributed by region — account and meter count per region, and what share of the total does each carry?
bar chart“Use platform metrics and developer feedback to inform conversations, challenge assumptions, and propose improvements.”
What is the HH vs NHH split across the meter population — how much of the book demands the technically demanding half-hourly data path?
bar chart“Evaluate platform approaches with commercial awareness, identifying cost-efficient infrastructure options.”
What is the smart-meter data quality SLO — how is last_read_days_ago distributed, and how many meters breach the platform read-freshness threshold?
deviation“Clearly articulate platform value and enable engineering teams to understand and adopt it.”
What does the fuel × meter-tech integration matrix look like — how many distinct processing paths does the platform need to support?
bar chart“Model ownership and accountability, supporting peers in developing the same behaviours.”
What is the month-by-month consumption data ingestion load — record counts and total kWh per month, ordered by calendar month?
bar chartThe honest other half. AI does the analysis; a person owns the decision — especially where regulation, fairness and accountability bite.
A plain-English question — the same one the job ad describes — is translated to SQL by the agentic backend.
Curated cards run server-side against MotherDuck when eligible. The workspace separately labels any local inspection path.
Runs against my_db.ensek_demo.accounts (27,640,145 rows declared by the manifest). No synthetic numbers.
Each figure carries a falsifier — recomputed from the result set, not a stored number, so it can't quietly drift.
It's the role getting done: curated questions run live server-side against the warehouse; local inspection is labelled inside the workspace.
Open the live workspace →Provenance. Representative ENSEK-style operational dataset (480 accounts · 728 meters · 5,676 monthly consumption records). Schema mirrors my_db.ensek_demo.accounts/meters/consumption_monthly. Seed 20260609 — reproducible. No real ENSEK or customer data. Live server-side path: my_db.ensek_demo.accounts (27.6M rows). Dormant until operator provisions MOTHERDUCK_TOKEN.
It's Sorted — I took ENSEK's job ads and didn't write a report on what AI could do. I built it. Get the rest sorted →
I'm trained on this proof and the real ENSEK: the Ignition meter-to-cash platform (seven modules), the move under Centrica in 2024, 7M+ energy accounts migrated for suppliers like British Gas and Utility Warehouse, and the Ofgem framing. Ask me how the Data Analyst function changes shape, or which open roles map to which Ignition module.