Lead Data Scientist

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 therefore not about inventing a new strategy from scratch. It 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 persons skill in engineering and software craft, has a big impact 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 rationalise duplication, inconsistency and unnecessary complexity.
• Develop, improve and productionise recommendation models across agreed customer and commercial use cases.
• Own the full recommendation model lifecycle:
• Data and feature development;
• Model development;
• Evaluation;
• Production implementation;
• Monitoring;
• Retraining;
• Ongoing optimisation.
• 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 behaviour and take ownership of model quality once live.
• Provide clear technical communication to both client stakeholders and the wider delivery team.

Requirements

This is a Data Science role with a much stronger production engineering expectation than a typical modelling-only position.

We are looking for someone with strong experience in:

• Recommendation systems, ranking or personalisation .
• Python in production Data Science environments.
• Databricks .
• PySpark / Spark .
• Large-scale customer, product or behavioural 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.

Relevant recommendation experience could include:

• Collaborative filtering;
• Content-based recommendation;
• Hybrid approaches;
• Candidate generation;
• Ranking;
• Learning to rank;
• Embeddings;
• Representation learning;
• Personalisation;
• Experimentation and incremental impact measurement.

Experience with MLflow, Delta Lake, Databricks Workflows and model lifecycle management would be highly valuable.

The strategic direction already exists.

The successful person needs to be comfortable coming into an established environment, understanding the current state quickly, and executing and improving the agreed approach .

You will likely be someone who has spent several years as a strong hands-on Data Scientist and has gradually taken on more responsibility for how your models are engineered, deployed and operated.

You should be equally comfortable:

• Discussing recommendation methodology;
• Reviewing model performance;
• Writing Python;
• Refactoring code;
• Designing clean class structures;
• Working in Databricks;
• Debugging PySpark;
• Writing tests;
• …