As a Lead Data Scientist at Leakmited, you will take full ownership of data science initiatives and drive them from idea to real-world application. You will be the main data science contributor on your projects, responsible for transforming complex data into robust, scalable solutions deployed in production.

You will work in close collaboration with software development, product, and operations teams to ensure that data science solutions are technically robust, operationally relevant, and deployable in real-world environments.

This role is ideal for someone who enjoys autonomy, responsibility, and hands-on problem-solving in a startup / scale-up environment.

Our technical stack: Python, geopandas, unity catalog, databricks, python notebooks, SQL, postgresql/postgis, DBT, github, github actions, AWS, mlflow, langchain/ langgraph/langsmith.

Your Responsibilities

• Explore, analyze, and model complex datasets related to water networks and leak detection.

• Design, develop, and validate machine learning and statistical models to identify leaks and optimize network performance.

• Own data science projects end-to-end, from initial exploration and hypothesis building to production deployment and monitoring.

• Collaborate closely with data and software engineers to integrate models into production applications.

• Work with Operations teams and field experts to understand real-world constraints and translate operational needs into data-driven solutions.

• Evaluate model performance, ensure robustness and reliability, and drive continuous improvement.

• Contribute to research and experimentation around new modeling approaches and methodologies.

• Clearly communicate insights, results, and limitations to both technical and non-technical stakeholders.

Your Profile

• At least 4+ years of professional experience as a Data Scientist, with proven ownership of at least one project from exploration to production deployment.

• Strong experience in data analysis, feature engineering, and model development.

• Hands-on experience and strong proficiency with at least three core technologies from our tech stack.

• Ability to work independently, take initiative, and act as the main data science referent on projects.

• Strong cross-functional mindset, with the ability to work comfortably with developers as well as non-technical teams (operations/field experts).

• Fluent English (professional).

• Curious, creative, and pragmatic problem solver with an impact-oriented mindset.

Nice to have

• Experience with geospatial (GIS) data and/or time-series data and/or hybrid physical and machine learning or deep learning approaches would be a plus.

• Previous experience in a startup or scale-up environment.

• Bachelor’s or Master’s degree in Data Science, Computer Science, Statistics, Applied Mathematics, or a related field.

1. Pre-screening with the Recruiter: Initial conversation to assess compatibility and present the role.

2. Interview with the Head of Data: Evaluation of technical skills and relevant experience for the position.

3. In-person Interview with the Team: Assessment of interpersonal skills, cultural fit, and deeper technical knowledge.

4. Final Interview with the CEO: Evaluation of strategic alignment and final discussion on the candidate’s potential impact.

5. Offer Presentation: Presentation of the offer and explanation of next steps.