Principal Data Scientist, Sparkbox

• Experience applying predictive machine learning in a commercial setting
• Proven track record of productionising ML-based products
• Ability to develop ML solutions from high-level requirements and ideas
• Strong Python skills (e.g., scikit-learn, pandas)
• Solid understanding of modelling techniques and their practical applications
• Proficient in SQL and handling large datasets
• Excellent communication skills, with the ability to explain complex ideas to non-technical stakeholders
• Some domain knowledge in retail or consumer goods, especially pricing or demand forecasting

• As Principal Data Scientist, you’ll lead our Data Science team and contribute directly to the development of our machine learning platform. You’ll work across the business to drive product innovation, develop team members, and help bring data science to life for our clients.
• We’re looking for someone who has strong technical and leadership skills and enjoys hands-on development. You’ll bring a strong engineering focus to how the team builds and scales data solutions, and a product lens that ensures our models deliver real value in the hands of users.
• Define and manage our data science roadmap
• Lead and mentor a team of data scientists, supporting their technical and professional growth
• Communicate progress and insights to internal teams and client
• Collaborate with:
• O Leadership team to translate client and business requirements into tasks, project plans, and priorities, and provide guidance on how data science activities can guide business growth
• O Development and Product teams to Frame data science outputs as part of a larger product and ensure data science development is correctly configured and deployed in our front-end applications
• O Customer Success to interpret outputs, troubleshoot problems, respond to customer queries, and develop new use cases/ features
• Guide team members in analysis, modelling, coding, and review code
• Investigate and resolve issues related to algorithms, logic, or performance
• Design, test, and improve machine learning models and productivity tools
• Lead deployment of data science assets in collaboration with engineering
• Integrate software engineering practices (e.g., modular code, testing, code review) and deployment best practices (e.g., CI/CD, containerization, monitoring) into end-to-end data science product development and delivery

• Apply via Welcome to the Jungle
• Virtual interview with Kevin, our co-founder and ML/Data lead
• In person interview with Kevin and our other co-founders, Lindsay and Matt. This will likely take place in London, and we may also ask you to bring along an example of your previous work

• 33 days holiday (25 days annual leave + UK bank holidays)
• Stock options - We offer team members part ownership of our company as we believe you should be rewarded for being part of our growth
• Flexible working - We are open to discussing part time or flexible working opportunities
• Occasional travel - To conferences, trade shows, or trips to work with colleagues in our London/Manchester hubs
• Extensive Development Opportunities: We encourage our team members to contribute based on their interests, and we’ll provide opportunities to work cross functionally across the business. Tell us what you need, and we’ll make it happen: we are committed to promoting great talent as our business and our needs grow
• Health cash plan
• Monthly team meetups with team lunch or drinks
• Biannual team parties

Total funding: $2.1m

Many retailers are still depending on antiquated manual processes to make inventory decisions. With the events of recent years, however, it’s become clear that failing to use accurate, data-driven insights to ensure good merchandise stock can take a heavy toll on business. Sparkbox is an AI-first startup hoping to change that. It helps brands optimise pricing, forecast demand, act on rebuying opportunities, and ensure their inventory is available across broader wholesale and 3rd party channels.