Data Scientist - Startup Berlin

Data Scientist - Startup Berlin

Cherry Ventures is supporting our portfolio with this hire

Berlin based - m/f/d - full-time

What we do at Plato

Plato is building the digital backbone of the global trade economy. Starting with the $48T wholesale industry, we empower the modern wholesaler to connect their people and data in a single analytics and workflow hub. By leveraging data science and AI, we automate workflows and combat labor shortages, making SMB wholesalers competitive with large corporations.

🎯 Why we do what we do

The future of wholesale is data-driven. Unlike popular opinion, Industrial SMEs are ready to make the step to become more proactive in their processes but lack the technology to steer them to success. Our founders come from a wholesale family and gathered a rock star team of ex-Big Tech, VC, and top-tier consulting companies to reshape the operations of this $48tn industry. Our initial product leverages cutting-edge data science to provide customized demand forecasts and product recommendations combined with intelligent workflow automation.

We are about to create category-defining software. Our primary customers are C-suite executives within large-scale wholesale and distribution businesses. We are committed to helping them enhance their decision-making processes and optimize their operations through the smart use of their data - bringing their operations into the 21st century! But don’t just hear it from us! We are supported by a list of top-tier EU & US VCs, advisors, and angels providing insights from some of the best SME tech companies such as Miro, Celonis, Personio, Workday, Forto, and Microsoft.

🔮 What we’re looking for

As a Data Scientist at Plato you will be tackling the complex challenge of building versatile models that serve multiple industries, ranging from construction and steel to technical and HVAC wholesalers. Each industry presents unique data sets and requires a tailored approach.

You will have the opportunity to develop a variety of models, such as recommendation engines, dynamic pricing systems, churn prediction models, and customer segmentation algorithms. You will be responsible for the entire lifecycle of these models, from creation to deployment, and ensuring they scale across different industries.

Our platform generates a wealth of data from user interactions, and a key part of your role will be feeding this data back into the models to continuously improve their performance. You’ll collaborate closely with our data engineering and product teams to ensure our portfolio of data products provide value to our users.

🚀 What you’d be working on

• Develop, test, and deploy a wide range of machine learning models, including recommendation systems, dynamic pricing models, churn prediction algorithms, and customer categorisation systems.
• Tackle the challenge of building adaptable models that can be customized across various industries, such as construction, technical, and HVAC wholesale, ensuring that industry-specific needs are met.
• Continuously refine and update models based on real-time platform data and customer feedback to ensure they evolve with our users’ needs.
• Collaborate with data engineers and ML engineers to build efficient data pipelines that feed into and optimise machine learning models.
• Design experiments to assess model performance and iteratively improve accuracy and scalability.
• Implement automated model retraining and monitoring systems to ensure that models remain relevant and continue to perform in production environments.
• Work closely with the product and engineering teams to align model outputs with business goals and deliver actionable insights to customers.
• Build processes to efficiently manage the lifecycle of machine learning models, including versioning, experimentation, and reproducibility across different deployments.

🏅 What you bring along

• 3+ years of experience in data science, with a strong emphasis on machine learning model development and deployment.
• Hands-on experience with recommender systems is highly valued—this will be a core component of the role.
• A strong generalist mindset, capable of owning the full product lifecycle—from translating business problems into data science solutions to building and maintaining models in production.
• Experience in building and running machine learning models end-to-end; you will own your models, ensuring they run smoothly in production and are continuously optimised.
• Experience with MLFlow for model tracking and lifecycle management is desirable.
• Hands-on experience with data engineering tools and platforms; a background in Databricks is highly valued.
• Familiarity with NLP techniques is a plus, especially for customer segmentation and categorisation tasks.
• Ability to wear multiple hats and thrive in a startup environment where flexibility and initiative are key.
• Proficiency in German is plus.

🛠️ The tools you will be using

• Python
• PySpark
• Databricks
• MLFlow
• Model Serving Technologies
• CI/CD Tools (e.g., Jenkins, Git)
• Cloud Platforms (AWS)
• Data Engineering Tools (Apache Spark, DBT)

Cherry Ventures is an equal opportunity employer and values diversity. We do not discriminate on the basis of race, religion, colour, national origin, gender, sexual orientation, age, marital status, or disability status.