Carbonfact

The fashion industry is responsible for 5–10% of global greenhouse gas (GHG) emissions. As pressure for climate action grows, more companies are turning to carbon management tools. But most platforms are generic, lacking the depth needed for driving real change in fashion. Carbonfact is the Environmental Intelligence Platform built specifically for the textile and fashion industry. We turn messy, real-world business data into environmental intelligence — enabling any fashion company to measure, model, reduce and report on its impact with confidence. We’ve raised $17M from top-tier investors including Alven, Headline, and Y Combinator, and we’re already trusted by leading brands like Carhartt, GANNI, On, Allbirds, Armedangels, Jack Wolfskin, and many more. Data Scientist at Carbonfact Our platform is organized around four pillars: Collect customer data through custom connectors, Measure impact from a single process to an entire brand, Reduce footprint through simulation tools, and Report with audit-ready, regulation-compliant outputs. As a Data Scientist, you sit at the heart of the Collect and Measure pillars. Fashion brands send us bills of materials, catalogs, purchase orders — in different formats, with gaps, inconsistencies, and ambiguities. You make that data flow: parsing, normalizing, enriching, filling the gaps, flagging anomalies, and connecting it to our LCA engine so brands can measure and reduce their footprint. You'll leverage AI as a power tool in your daily work to keep our connectors lean. What matters is your judgment on data quality, ability to write production-grade code, and instinct for spotting what's wrong in a dataset before it reaches a customer. You'll work closely with customer data, joining client calls (a couple per week) and visiting brands onsite once or twice a year. Think of it as applied data work with a direct line to impact — every dataset you clean and every anomaly you catch, translate into a more accurate measurement of environmental footprint for a real product on a real shelf. Carbonfact's product is a Data Platform so you work is at the core of our value proposition. What you will do Parse, normalize, and transform raw business data (BOMs, catalogs, purchase orders) into Carbonfact's internal data models Build and improve automated gap-filling and anomaly detection on customer datasets Develop analytics on customer data for both internal use and external presentation to brands Contribute to building and improving the Carbonfact platform Partner with Customer Operations and Science teams to deliver value to customers Handle technical integration discussions with customers What you won't do Train machine learning models. We use frontier AI models extensively — we don't build them. Your value is in judgment and domain expertise, not gradient descent. Build heavy ETL pipelines. We maintain light connectors to our clients' diverse IT systems and spreadsheets. No Airflow DAGs, no Spark clusters, no data warehouse plumbing. Work in isolation. We build analytics to enable real decisions by the customers. You will own the delivery of data insights to help customers meet their decarbonization goals. Who you are You have 2+ years of professional experience Strong applied Python skills — you can build and improve our internal tooling, not just use it You are used to (or getting used to) leveraging agentic engineering to build a sustainable and healthy codebase Solid software engineering fundamentals: clean code, unit tests, version control — we have a high bar for code quality Comfortable with NLP basics: regex, typo handling, normalization, fuzzy matching SQL skills and curiosity for analytics engineering You communicate well in English and can discuss technical concepts with customers You're excited by heterogeneous, real-world data — the messier, the more interesting Bonus: data engineering experience or familiarity with environmental data What we offer A transparent, collaborative and h