Climate Tech Data Engineer Intern – Hybrid (London)

Carbon13 group; Greater London; Hybrid; GBP 23,000 - 29,000; Full time

Benefits offered by this job

25 days paid time off

Flexible hours

Team socials

Real ownership of a data project

Job summary

Kestrix, a London climate tech startup, is seeking a Data Engineering & Automation Intern to build a Python pipeline that extracts structured data from building survey PDFs. The data will be linked to image annotations to validate AI algorithms and enable scalable decarbonisation projects.

The role involves parsing retrofit reports and borescope documents, collaborating with the engineering team, and contributing to data campaigns. Hybrid work in London is available, with ownership from day one.

Qualifications

• Strong Python and SQL skills for data extraction.
• Experience with data modelling and databases.
• Ability to handle messy real-world data.
• Clear communication and independent work style.

Responsibilities

• Write Python to parse retrofit assessment and borescope reports with varying layouts and terminology, using LLM APIs and document-extraction tools.
• Link extracted data to existing image annotations to create ground-truth datasets for algorithm validation.
• Support the ground-truth data collection campaign as needed.
• Work closely with the engineering team on technical decisions and platform integration.

Skills

Python

SQL

Data modelling

Tools

LLM APIs

Document-extraction tools

Job description

Kestrix, a London climate tech startup, is seeking a Data Engineering & Automation Intern to build a Python pipeline that extracts structured data from building survey PDFs. The data will be linked to image annotations to validate AI algorithms and enable scalable decarbonisation projects.

The role involves parsing retrofit reports and borescope documents, collaborating with the engineering team, and contributing to data campaigns. Hybrid work in London is available, with ownership from day one.