Remote Data Engineer — End-to-End Pipelines for AI

CARBONAI LIMITED; Greater London; Remote; GBP 54,000 - 66,000; Full time

Benefits offered by this job

Ownership of systems

Remote work

London office visits

Growth opportunities

Job summary

CARBONAI LIMITED in London is seeking a Data Engineer who will own the data pipelines powering our climate data platform. You'll pull data from APIs, files and the web, transform messy sources into AI-ready material, and ship robust, observable code.

You'll collaborate with product and AI teams, design document chunking for RAG, deploy in the cloud, and ensure data quality. The role is primarily remote with occasional London office visits, offering real ownership and growth opportunities.

Qualifications

• 3-5 years of experience in data engineering or a similar role.
• Strong, production-quality Python.
• Good SQL and relational database skills.
• Experience pulling data from REST APIs and files (CSV, Excel, JSON).
• Web scraping experience (BeautifulSoup, Scrapy or Playwright).
• Experience extracting content from PDFs and documents.
• Hands-on experience chunking documents for RAG.
• Infrastructure-as-Code.
• Embeddings and vector databases (RAG).
• Measuring and improving retrieval quality.
• Interest in climate or carbon markets.

Responsibilities

• Build and run Python pipelines that collect data from APIs, CSVs and other structured sources.
• Scrape registry and market websites where there's no API, and make those scrapers reliable.
• Extract text, tables and metadata from PDFs and other documents.
• Design how documents are chunked for RAG so our AI finds the right passage.
• Keep data clean, tested and monitored so problems are caught early.
• Deploy and run your pipelines in the cloud.
• Work with AI as an everyday coding and work partner, while staying fully in charge of what you ship.
• Work closely with product and AI colleagues, and help shape what we build next.

Skills

Python

SQL

REST APIs

Web scraping

PDF extraction

RAG chunking

Infrastructure-as-Code

Embeddings

Vector databases

Retrieval quality

Climate/carbon markets interest

3-5 years experience

Tools

BeautifulSoup

Scrapy

Playwright

Infrastructure-as-Code

Job description

CARBONAI LIMITED in London is seeking a Data Engineer who will own the data pipelines powering our climate data platform. You'll pull data from APIs, files and the web, transform messy sources into AI-ready material, and ship robust, observable code.

You'll collaborate with product and AI teams, design document chunking for RAG, deploy in the cloud, and ensure data quality. The role is primarily remote with occasional London office visits, offering real ownership and growth opportunities.