Data Engineer

CARBONAI LIMITED; Greater London; Remote; GBP 54.000 - 66.000; Vollzeit

Benefits dieser Stelle

Ownership of systems

Remote work

London office visits

Growth opportunities

Zusammenfassung

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.

Qualifikationen

• 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.

Aufgaben

• 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.

Kenntnisse

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

Jobbeschreibung

Location: London, UK (primarily remote, with office visits 1–2 times a month)

Type: Full-time · Salary: Up to £60,000

Carbon markets only work if people can trust the data behind them. At CarbonAI we bring together project data, pricing, ratings and thousands of registry and methodology documents so buyers, investors and developers can make better decisions about carbon credits.

We're looking for a Data Engineer to own the pipelines that power this. You'll pull data from APIs, files and the web, turn complex documents into material our AI can use, and decide how it all gets built. We hire smart, careful people who communicate well, and then we give them real ownership.

What you'll do

• 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, including messy ones
• Design how documents are chunked for RAG so our AI finds the right passage every time
• 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

About you

We care more about how you think and work than about ticking every box below. You'll do well here if you:

• Learn quickly and enjoy figuring out unfamiliar data and tricky problems
• Take care over the details, finish what you start, and leave things well documented
• Explain your thinking clearly in writing and in conversation, and raise issues early
• Like owning a problem from start to finish, without waiting to be told each step

You'll need

• 3-5 years' experience in data engineering or a similar role
• Strong, production-quality Python
• Good SQL and relational database skills
• AI tools built into how you work every day (e.g. coding assistants, agents), plus a commitment to understanding the code they produce and how the pieces fit together
• Experience pulling data from REST APIs and files such as CSV, Excel and JSON
• Web scraping experience (e.g. BeautifulSoup, Scrapy or Playwright)
• Experience extracting content from PDFs and other documents
• Hands-on experience chunking documents for RAG
• Infrastructure-as-Code
• Embeddings and vector databases (RAG)
• Measuring and improving retrieval quality
• An interest in climate or carbon markets (no prior knowledge needed)

What we offer

• Real ownership of the systems you build, and a say in tools and architecture
• A small team that trusts people, with clear goals and no micromanagement
• Work that makes carbon markets more transparent and more trustworthy
• Room to grow into AI engineering or wider platform work
• Primarily remote working, with occasional visits to our London office