Data Scientist

📋 Description

• • Join Fingerprint, a globally dispersed, 100% remote company at the forefront of online fraud detection, and contribute to turning radical new ideas into reality. We are a well-funded startup, having raised $77M from top-tier investors like Craft Ventures, Nexus Venture Partners, and Uncorrelated Ventures, and are proud of our strong open-source focus, exemplified by our flagship project, FingerprintJS, which boasts over 20,000 stars on GitHub.
• • As a Data Scientist, you will play a pivotal role in enhancing the accuracy of our Smart Signals by applying sophisticated data science and machine learning techniques within a high-load, real-time service environment. This is an opportunity to tackle challenging ML problems and contribute across the entire project lifecycle, from initial prototyping to final deployment.
• • Your primary responsibility will be to develop innovative algorithms capable of transforming raw, noisy, and often unlabeled data into actionable insights about browsers and devices. This involves deep dives into complex datasets to identify patterns and anomalies that are crucial for our fraud detection capabilities.
• • You will design, implement, and refine supervised learning models to significantly improve our detection accuracy. This includes leveraging techniques such as gradient boosting and logistic regression, with a particular focus on effectively handling categorical data, a common challenge in this domain.
• • Collaboration is key to our success. You will partner closely with a talented team of ML Engineers, fellow Data Scientists, and Software Engineers, contributing to the collective advancement of our technical expertise and pushing the boundaries of what's possible in fraud detection.
• • Conduct thorough exploratory data analysis to investigate anomalies, uncover hidden trends, and answer ad-hoc questions that arise from our vast datasets. This analytical rigor is essential for understanding user behavior and identifying potential fraud vectors.
• • Design and execute experiments to address critical ML engineering challenges, including optimizing real-time inference performance and automating training processes. This ensures our models are not only accurate but also efficient and scalable in a production environment.
• • Work with a modern tech stack that includes Python, Go, SQL, and various ML frameworks for backend and data science tasks. You'll also utilize analytics and processing tools like ClickHouse and dbt, and leverage AWS for infrastructure. This exposure will provide a comprehensive understanding of a cutting-edge data science workflow.
• • As part of a fully remote team, you will be proficient in using collaboration tools such as Slack, Google Workspace, and Zoom, ensuring seamless communication and productivity regardless of your location. You will also be comfortable working within the macOS environment.
• • This role offers the chance to make a tangible impact on a product used by developers worldwide, from individual creators to large enterprises. Your work will directly contribute to building a safer online environment by empowering developers to stop fraud at its source.
• • You will be encouraged to bring your academic or research background to bear, potentially exploring semi-supervised or unsupervised learning techniques, and contributing to the intellectual capital of the team. Experience with visualization tools and analytical storage systems will be highly beneficial in translating complex data into understandable insights.
• • The opportunity to build lightweight real-time services from ML models will allow you to see your work deployed and directly impacting our product's performance and capabilities. This end-to-end involvement is a hallmark of our development process.
• • We are committed to fostering an inclusive and diverse work environment, encouraging applications from individuals of all backgrounds, particularly those from underrepresented groups in tech. Your unique perspective will be valued and contribute to our innovative culture.