Junior Data Scientist - Detection

Who are we? Hi! 👋 We are Ravelin! We're a fraud detection company utilizing advanced machine learning and network analysis technology to tackle major problems. Our aim is to make online transactions safer and assure our clients in serving their customers confidently. And we have fun doing it! We are a friendly team and we pride ourselves in nurturing a strong culture and staying true to our values of empathy, ambition, unity, and integrity. We highly value work-life balance and we adopt a flat hierarchy structure across the company. Join us and you'll quickly learn about cutting-edge tech and work alongside some of the brightest and kindest people in the business - If this sounds like your kind of environment, we would love to hear from you! For more information, visit our to see if you would like to help us prevent crime and safeguard the world's massive online businesses. The Team You will be joining the Detection team. This team is tasked with keeping fraud rates minimal and clients satisfied by regularly training and deploying machine learning models. Our objective is to make model deployments as effortless and error-free as code deployments. We refer to Google’s as our guide. Our models are trained to identify multiple types of fraud, using a range of data sources and techniques in real time. The prediction pipelines are subject to strict SLAs, requiring every prediction to be returned in less than 300ms. It is then up to the Detection team to investigate should the models not perform as expected. The Detection team holds a central position in Ravelin’s achievements. They closely work with the Data Engineering Team responsible for infrastructure building and the Intelligence & Investigations Team assisting clients. The Role We are presently recruiting a Data Scientist to assist in training, deploying, debugging, and evaluating our fraud detection models. Our ideal candidate is practical, approachable, and well-experienced. Evaluating fraud models is complex; often, we don’t even get labels for 3 months. You’ll need to utilize your judgement when investigating cases of ambiguous fraud and verifying the accuracy of the model itself. We must build robust models capable of updating their understanding upon encountering new fraud strategies: our clients expect us to stay one step ahead of fraud, not trailing behind it. You will be equipped with the tools, space, and guidance necessary to develop world-class fraud detection models. Progress towards improved models for our clients is often about secure incremental advancements, not just about pioneering research. The ideal candidate is ready to engage in both aspects of the job – and understands why both are crucial. Responsibilities

• Expand our model evaluation and training infrastructure.
• Design and deploy new models to identify fraud while adhering to SLAs.
• Introduce new features in our production infrastructure.
• Research new strategies to thwart fraudulent behavior.
• Examine model performance issues (utilizing your experience in debugging models).

Requirements

• Around 1 year's Experience in creating and deploying ML models using the Python data stack (numpy, pandas, sklearn).
• Robust analytical skills.
• Excellent collaboration skills with colleagues outside your immediate team, such as with client support teams or engineering.
• Ability to communicate complex technical concepts to a range of audiences.
• Excellent prioritizing skills and the ability to manage your workload.
• Comfortable working in a hybrid team.

Nice to haves

• Understanding software engineering best practices (version control, unit tests, code reviews, CI/CD) and how they apply to machine learning engineering.
• Experience with Tensorflow and deep learning.
• Experience with Kubernetes and ML production infrastructure.
• Experience with Go, C++, Java, or another systems language.

Benefits

• Flexible working hours, hybrid working model, Old Street office, and a £500 home office budget.
• Share options.
• 25 days holiday + bank holidays + an additional day off per year of service (up to 5) + 1 extra day off for cultural reasons.
• Extra monthly company-wide days off - the Wellbeing & Learning Days.
• £1000 annual wellbeing budget to spend through Heka.
• Mental health support through Spill.
• Comprehensive medical coverage with AXA, including pre-existing conditions.
• Pension Scheme with Aviva.
• Increased parental benefits.
• Company socials, team social, and budget for micro-socials that anyone can organize for any event.
• Ravelin Gives Back (RGB) - monthly charitable donations and regular volunteering opportunities.
• Bi-weekly team lunches with a random group from the company, either in-person or virtually (via Deliveroo).
• Access to BorrowMyDoggy.
• Can avail tax-efficient bicycle purchase via the Cycle-to-Work scheme.
• Weekly board game nights.

*Job offers may be revoked if candidates fail to pass our pre-employment checks: unspent criminal convictions, employment verification, and right to work.*