Sr Data Scientist

Sibill is the accounting and financial operating system for small and medium businesses (SMBs). Outdated tools and fragmented data waste entrepreneurs a lot of hours each week — we give this time back by integrating invoicing, payments, treasury, and accounting in one modern platform.
We’re backed by top international investors such as Keen Venture Partners (Fiscozen), Founders A/S (Pleo), Exor Ventures (Qonto, Alan), Notion Capital, and most recently Creandum, known for supporting Klarna and Spotify at early stages.

Thousands of entrepreneurs already trust Sibill.

Our goal? Reach millions. This is just the beginning.

What we look for

We are looking for a motivated, pragmatic, and goal-oriented Senior Data Scientist to join our Data team.

You are the perfect fit if...

• You are passionate about technology, statistics and business. The three of them.

• You don’t feel “done” yet, you want to keep learning and applying science to drive business outcome. You still want to be hands-on.

• You are excited about working in a flat, no-politics, fast-paced environment.

• You have excellent analytical skills and and a sharp eye for detail.

• You are not scared of working hard. As a team, we all have to go the extra-mile to make it happen.

• You feel like fitting the values we share at Sibill: ambition, pragmatism, efficiency, integrity

What you will do

You will report directly to Dario, the Chief Data Officer & Co-Founder. With Dario you will build all the data products that empower our customers to run their business better. This will not be a one-man standing. It will take a lot of cross-functional work with the people in our data, engineering, product, design teams.

We sit on top of the most business-critical company data. Money flows, bank transactions, invoices, cash register records, payables and receivables, general ledger records. We are the accounting & finance operating system of our customers. You will build data products that use this vast information set to solve specific customer problems.

Your responsibilities will include:

• Discovery, domain understanding, data collection and experimentation

• Model development (training / test / validation)

• Performance monitoring and iteration over existing data products

Examples of projects you could work on from month one at Sibill:

• Refining our auto-reconciliation search algorithm (matching invoices with related financial money flows) to try and improve f-score.

• Building a classification model to label general ledger records with the right chart of accounts codes.

Who you are

• M.Sc./Ph.D. in Data Science, Statistics, Computer Science, Mathematics or a related STEM field. You won’t be asked to send rockets to Mars - but a solid background in probability, stats, linear algebra and computational mathematics will give you an edge.

• Modern Python and modern software development tools (Docker, CI/CD, unit testing, evals). We do not run data pipelines built on Jupyter Notebooks in production. Bonus point if you know you way around vector stores.

• Proven expertise in leading model development using a wide range of techniques. Previous expertise in domains with high usage of neural networks (NLP, computer vision) is highly beneficial.

• Especially at the beginning, an end-to-end data ownership mindset. It will not happen every day but - if necessary - you might be asked to build your own data pipeline end-to-end, to write a batch ETL, to write Elixir or TypeScript code, or to support teammates with an important one-off empirical analysis.

• Fluency in English and Italian.

• Bonus point: at least 7-8 years of experience. You have already coached and mentored junior colleagues.

Comp & Benefits

• RAL: range between 70-90k €, based on your experience

• Meal voucher: (8€/business day)

• Full remote (based in Italy). We will just ask you to come to Milan for a few weeks during the onboarding (trip is on us)

• You will work within a team of smart, hard-working, passionate and nice human beings. People in Sibill tend to be very happy. Happiness is an underrated benefit ;-)

Recruiting process

1. a quick chat with Gaia, our HR Manager

2. 30 minutes “know-each-other” session with Dario (Chief Data Officer)

3. 45 minutes technical interview

4. you will meet some of the key people you will work with (engineering, data, product)

5. 45 minutes with Mattia (CEO) and Lorenzo (Chief Product Officer)