About the Position

Lead Data Scientist

Cluj-Napoca, Cluj County, Romania

At Mindera, we believe that software is built by people, for people, with high-performance systems that impact users worldwide. We are looking for a Lead Data Scientist to join an agile, collaborative team where your voice matters as much as your code.

This role is about taking an agreed plan, implementing it well, and owning the recommendation models end to end in production. We value empathy, self-organization, and a positive attitude. If you are approachable, communicate clearly, and believe that team fit is just as important as technical expertise, you'll feel right at home here.

At Mindera we encourage the use of AI to assist with coding and related tasks. We find a person's skill in engineering and software craft has a big impact on long-term successful delivery, with or without AI. Our goal in the interview process is to understand the candidates' knowledge and skill with engineering.

If you need to, or plan to use AI, please be transparent with us when you're using it, to avoid issues and misunderstandings that can either: impact your chance of securing the role or impact your success at Mindera.

National and international expected traveling time varies according to project/client and organizational needs: 0%-15% estimated.

How You'll Contribute:

You will work closely with the Data Science leadership, engineering teams, becoming the senior hands-on Data Scientist responsible for progressing the recommendation capability in a disciplined and maintainable way.

Lead the consolidation of existing recommendation algorithms into a simpler, more coherent recommendation capability.
Implement the client’s existing technical direction and agreed delivery plan.
Review current recommendation approaches and rationalize duplication, inconsistency, and unnecessary complexity.
Develop, improve, and productionize recommendation models across agreed customer and commercial use cases.
Own the full recommendation model lifecycle:
Work directly in Databricks, using Python and PySpark to develop scalable production workloads.
Refactor exploratory or notebook-based Data Science code into maintainable production implementations.
Apply strong object-oriented design and software engineering principles to the recommendation codebase.
Create reusable and testable components for areas such as candidate generation, scoring, ranking, feature generation, and evaluation.
Build appropriate automated testing around Data Science and ML code.
Work with engineering and platform teams on production integration without handing off ownership of the models themselves.
Define and maintain clear offline evaluation frameworks.
Support online experimentation and measurement of recommendation effectiveness.
Monitor production behavior and take ownership of model quality once live.
Provide clear technical communication to both client stakeholders and the wider delivery team.

Responsibilities

Lead the consolidation of existing recommendation algorithms.
Implement the client’s existing technical direction and agreed delivery plan.
Review current recommendation approaches and rationalize duplication, inconsistency, and unnecessary complexity.
Develop, improve, and productionize recommendation models.
Work directly in Databricks, using Python and PySpark.
Refactor exploratory or notebook-based Data Science code into maintainable production implementations.
Apply strong object-oriented design and software engineering principles.
Create reusable and testable components.
Build appropriate automated testing around Data Science and ML code.
Work with engineering and platform teams on production integration.
Define and maintain clear offline evaluation frameworks.
Support online experimentation and measurement of recommendation effectiveness.
Monitor production behavior and take ownership of model quality.
Provide clear technical communication to stakeholders.

Requirements

Recommendation systems, ranking, or personalization.
Python in production Data Science environments.
Databricks.
PySpark / Spark.
Large-scale customer, product, or behavioral datasets.
Object-oriented programming.
Clean code and software design principles.
Modular, reusable, and testable ML code.
Unit testing.
Git-based development.
CI/CD practices for Data Science or ML workloads.
Model evaluation and experimentation.
Deploying models into production.
Monitoring and maintaining production models.

Nice to Have

MLflow.
Delta Lake.
Databricks Workflows.
Model lifecycle management.

We Offer

THE PERKS OF BECOMING A MINDER:

Private medical subscription
Private medical subscription for children
Counseling and psychotherapy services
Reimbursement for eyeglasses
Self-proposal salary process
Annual profit distribution, subject to company performance and board decision
Mindera Unit Plan
Flexible benefits options (sports, medical, cultural, donations)
Trainings and learning opportunities to grow within your role
Coaching and development guidance
25 days holiday
Flexibility to choose where you work from
Vacation incentive
Parties, gatherings & trips

About the Company

We're thrilled to have the opportunity to share with you what it's like to be a part of the Mindera community.

We're a group of friendly and talented individuals who work together to bring projects to life, in a fun, politics-free environment.

Our culture is all about being adaptable and self-organized. We want Minders to take risks, make decisions, work together, and feel free to be their most authentic selves, every single day.

We work closely with our clients to truly understand their products and develop high-performance, resilient, and scalable software systems that make a real impact for their users and businesses, worldwide.

We are proud of our work, we're always learning and growing in our Agile and collaborative environment, and we hope you'll love it here just as much as we do!

Check out our Handbook & get to know us better: Mindera Handbook

Lead Data Scientist

Job description