Staff Data Scientist

Summary

Join Zepz's FinCrime team as a lead data scientist and advanced analytics expert. You will spearhead data science initiatives, challenge model assumptions, and shape the development of data pipelines and machine learning systems using technologies like Airflow, Fivetran, DBT, Databricks, and DynamoDB. Responsibilities include owning delivery, mentoring junior team members, and collaborating with various stakeholders. The ideal candidate possesses extensive experience in designing and productionizing ML systems, a strong understanding of machine learning fundamentals, and excellent communication skills. Zepz offers a remote-first work environment and benefits such as unlimited annual leave, private medical cover, retirement plans, life assurance, and parental leave.

Requirements

• You are a software engineer at heart, and you take pride in writing well-designed, robust, and maintainable code to solve problems. We understand code is read more than it’s written, and better off tested. Maintainability is a must
• Extensive Industrial experience designing and productionising ML systems
• Solid understanding of Machine Learning fundamentals and ability to translate business requirements into machine learning solutions
• Experience in statistical experiment design and performance analysis of machine learning models
• Strong experience with Python, SQL and machine learning frameworks
• Excellent communication and presentation skills, with the ability to convey complex concepts to technical and non-technical stakeholders
• Bias for action. You see a problem, you fix a problem. You get buy-in for your solutions and keep tickets moving. We’re always looking for ways to ship at pace
• Opinionated. We want you to actively contribute to discussions and help build a shared understanding within the team and organisation

Responsibilities

• Be the lead of our data science and advanced analytics initiatives across the FinCrime team
• Constantly challenge our own assumptions in models - our “target audience” has a huge incentive to change their behavior to evade detection
• Help shape what we build. Our current tech stack includes Airflow, Fivetran, DBT, Databricks and DynamoDB and is primarily in Python, leveraging some of the most used machine learning packages. You will build and maintain data pipelines and scalable machine learning inference systems in production
• Own delivery. We’re driven by shipping value; you’ll own work beyond just a pull request. You’ll care about bugs, scalability, uptime and other non-functional requirements
• Grow together. You’ll review other’s work and happily seek feedback on yours to ensure we build a better codebase and sharpen each other's skills. We believe in developing our people so you will be an important part of mentoring juniors in the team
• Collaborate. You’ll be working closely with Product Owners, Data Scientists, Analysts and other Engineers to design and refine our work. We work as a team and your input will be key in many architectural decisions (some that you would own) and in driving consensus

Preferred Qualifications

Some data engineering experience is preferred (Databricks and Airflow are some of the platforms we use, but any equivalent experience is appreciated)

Benefits

• Unlimited Annual Leave: Feel free to make the most of your time off and maintain a healthy work-life balance!
• Private Medical Cover: ​​You can opt-in to a Private Medical Insurance scheme. This provides you with access to thorough medical coverage, so you can feel confident in your health and well-being
• Retirement: We offer pension schemes to help you plan for and secure your future
• Life Assurance: Life assurance is available to give you peace of mind and protect your loved ones in case of the unexpected
• Parental Leave: We offer competitive parental leave schemes to ensure you are spending as much quality time with your new bundle of joy as possible
• We are also remote-first as an organisation, offering flexibility for you to work where you need to be most productive