Data Scientist, Lendable

• Experience using Python and SQL
• Strong proficiency with PyData stack
• Knowledge of machine learning techniques and their respective pros and cons
• Confident communicator and contributes effectively within a team environment
• Self driven and willing to lead on projects / new initiatives

Desirable

• Take ownership across a broad remit. You are trusted to make decisions that drive a material impact on the direction and success of Lendable from day 1
• Work in small teams of exceptional people, who are relentlessly resourceful to solve problems and find smarter solutions than the status quo
• Build the best technology in-house, using new data sources, machine learning and AI to make machines do the heavy lifting
• We are excited to be hiring a new Data Scientist into our team! Lendable is the market leader in real rate risk-based pricing, offering consumers transparency and product assurance at the point of application
• . Data Science sits at the heart of this USP, developing the credit risk models to underwrite loan and credit card products
• You will have access to the latest machine learning techniques combined with a rich data repository to deliver best in market risk models
• The data science team develops proprietary behavioural models combining state of the art techniques with a variety of data sources that inform market-facing underwriting and pricing decisions, scorecard development, and risk management
• Data scientists work across the business in a multidisciplinary capacity to identify issues, translate business problems into data questions, analyse and propose solutions
• We self-serve with all deployment and monitoring, without a separate machine learning engineering team
• Design, implement, manage and evaluate experiments of products and services leading to constant innovation and improvement
• Learn the domain of products that Lendable serves, understanding the data that informs strategy and risk modelling is essential to being able to successfully contribute value
• Rigorously search for the best models that enhance underwriting quality
• Clearly communicate results to stakeholders through verbal and written communication
• Share ideas with the wider team, learn from and contribute to the body of knowledge

• Initial call with TA
• Take home task
• Task debrief and case study interview
• Final interviews with Exec team