Paylead’s core business is valuing bank transaction data. Volume and sparsity of this data require to use advanced data collection, data engineering and data science techniques. In this context our Data team is expanding and we are now looking for a Machine Learning Engineer.

The team is composed of engineers with different backgrounds and experiences both in the industry and academia. We expect you to bring your experience, your knowledge, your curiosity to keep learning, your Passion for Excellence and Hard Work and above all your Team Play mindset.

ROLE & RESPONSIBILITIES

• Review (understand and have a critical look on) models and algorithms built by Data Scientists (DS)
• Deploy these models on Paylead Platform: This includes rewriting some parts of the code written by DS to improve scalability and time processing. This also includes building the backend code around the models (data preparation, apis, etc)
• Ensure monitoring and support of these models
• Be proactive on all Machine Learning related topics at Paylead

SKILLS & EXPERIENCE

• At least 2 years of experience in Data / Machine Learning Engineering, in companies with proven scaling track records and tech superiority on the market.
• Python proficiency and especially in its data science libraries (Tensorflow, Sklearn)
• SQL proficiency
• High sensitivity to code quality, robustness, time processing and scalability
• Pronounced taste for production environments
• Knowing the math’s behind standard machine learning models (algorithms, performance metrics, limitations). In particular having a good knowledge on few NLP models.
• Knowing most common machine learning use cases (prediction, recommendation, etc.)
• Good amount of knowledge on common development tools: GIT / Github/ …
• Strong inclination to propose new services, improvements, POC
• Strong curiosity with active watch on machine learning and bank transaction data topics, taking part in related events, (as participant or organizer)
• Paying a continuous attention to Data Privacy and user’s value maximization

Short call with Alexis our CDO, then meeting with the data team, then meeting with our backend team
and finally meeting with our cofounders.

NB : an additional short technical test @home might also be asked.