About the Role

We are looking for a Technical Lead, Data Science to build and lead our data science efforts, which lie at the heart of our fintech platform’s value proposition. In this role, you will own the development of machine learning models and data-driven algorithms that power features like real-time fraud detection, customer risk scoring, and identity verification. As the first data science hire (and leader), you’ll set the direction for how we leverage data to make smarter decisions and improve the safety and efficiency of digital payments. This is a chance to architect our data strategy from scratch – from defining what data to collect, to how we derive insights and integrate predictive models into our product.

Your day-to-day work will span from hands-on data exploration and model building to high-level strategy. One day you might be prototyping a new machine learning model to detect fraudulent transactions using patterns in account behavior; another day you might be working with engineers to productionize an identity scoring algorithm or designing the data pipeline that feeds our risk engine. You will also analyze data on user behavior, payment success rates, and fraud incidents to provide actionable insights. As the Technical Lead, you will collaborate cross-functionally – working with the Risk Analyst on tuning fraud rules, with Product on new features (e.g. adding a credit risk model for higher-value transactions), and with Engineering to ensure our systems can support data-intensive operations.

This role requires both technical excellence and leadership. You should be excited to both delve into coding and mathematics and to set a vision for a small data team. Over time, you will hire and mentor data scientists or analysts as the company grows. In the early stage, you’ll need to be resourceful, using open-source tools and clever techniques to get the job done quickly. This is a full-time position based in Denver, CO (hybrid/remote is OK) offering a competitive base salary and significant equity upside. If you are passionate about using data and AI to solve fintech challenges and want to have a major influence on product direction, this role is for you.

Key Responsibilities

• Model Development – Research, design, and implement machine learning models to address key needs of the platform: fraud detection (flagging suspicious transactions in real-time), risk scoring (quantifying the trustworthiness of users or accounts), identity verification (detecting anomalies or synthetic identities), etc. Utilize techniques from classification, anomaly detection, and network analysis to improve platform security and efficiency.

• Data Pipeline & Strategy – Define what data we need and work with engineers to build robust data pipelines that collect, clean, and store that data (e.g. transaction histories, user profiles, device data). Ensure data quality and reliability for both offline analysis and real-time scoring.

• Insights & Analysis – Analyze platform data to uncover trends and insights. For example, monitor fraud incident rates, model accuracy, customer behavior patterns, and present findings to the team to inform business decisions or product tweaks. Develop dashboards or reports for key data metrics related to risk and performance.

• Collaboration on Product Features – Partner with product managers and engineers to integrate your models into the product. This might include embedding a fraud detection model into the transaction processing flow or providing risk score outputs that trigger certain user experiences (like additional verification if risk is high). Ensure that data science solutions are feasible within the technical constraints and meet product requirements for response time and scalability.

• Iterate and Improve – Continuously monitor model performance in production. Tune and retrain models to maintain effectiveness as data distributions or fraud tactics evolve. Investigate false positives/negatives and adjust features or algorithms to improve accuracy over time.

• Compliance and Ethics – Work with the compliance team to ensure our algorithms meet regulatory requirements and ethical standards. For instance, ensure that our risk scoring methods are explainable and do not unfairly bias against any group, and assist in generating documentation for model governance.

• Leadership & Team Building – As the Data Science Lead, establish best practices for the data science function (coding standards, experiment tracking, validation methods). Mentor any future data scientists or analysts; review their work and guide their professional development. Lead the effort in selecting tools and technologies for data science (e.g. data analysis libraries, ML frameworks, etc.).

• Cross-Functional Communication – Translate complex data findings into layman’s terms for leadership and other departments. Provide data-driven recommendations to support strategic planning, such as identifying new product opportunities or advising on risk controls based on model predictions.

Required Qualifications

• Data Science Expertise – 5+ years of experience in data science or applied machine learning roles, with a strong foundation in statistics and algorithms. Proven track record of building models that have driven tangible improvements in a product or business.

• Programming & Tools – Proficiency in Python (or R), including common data science libraries (pandas, scikit-learn, TensorFlow/PyTorch, etc.). Comfortable with SQL for data querying. Experience with data visualization tools to communicate findings.

• Machine Learning & Analytics – Hands-on experience with a range of ML techniques (supervised and unsupervised learning). Ability to choose the right approach for a given problem – from logistic regression and decision trees to neural networks or anomaly detection algorithms. Strong analytical thinking and ability to interpret model results.

• Domain Familiarity – Understanding of fraud detection, risk modeling, or fintech analytics is highly advantageous. If no direct fintech experience, must demonstrate ability to quickly learn domain specifics (e.g., knowing what features might indicate a fraudulent payment vs a legitimate one).

• Software Engineering Basics – Experience deploying models into production environments. Knowledge of version control (Git), and comfort with software development practices to ensure your code is maintainable by engineers. Ability to optimize code for performance when working with large datasets or real-time requirements.

• Leadership & Autonomy – Self-directed and able to set your own goals based on high-level company objectives. Experience leading projects or mentoring junior data scientists/analysts. Excellent organizational skills to manage an end-to-end workflow from data extraction to model deployment.

• Communication – Strong ability to communicate complex quantitative analysis in a clear, precise, and actionable manner. Able to write documentation and present results to non-technical stakeholders effectively.

• Education – Advanced degree (Ph.D. or Master’s) in Data Science, Computer Science, Statistics, or a related field is preferred; or a Bachelor’s with equivalent practical experience in data-centric roles.

Preferred Qualifications

• Fintech/Risk Experience – Previous work in a fintech startup, bank, or payments company focusing on things like credit risk modeling, fraud analytics, or customer segmentation. Familiarity with regulatory frameworks around financial data (e.g., FAIR lending laws, model risk management guidelines) can be a plus.

• Graph and Network Analysis – Experience with graph databases or network analysis techniques, which can be useful for identity resolution and detecting fraud rings (for example, analyzing how accounts/devices are interrelated).

• Real-Time Data Processing – Exposure to streaming data platforms (Kafka, Kinesis, etc.) or real-time scoring systems. Ability to design models or rules that operate within sub-second decision windows for live transaction monitoring.

• Big Data Technologies – Familiarity with big data tools (Spark, Hadoop) or cloud-based analytics platforms that might be used as our data scales. Experience with cloud ML services (like AWS SageMaker, Google ML Engine) for managing production models.

• Business Insight – Strong business acumen to prioritize data science efforts with the highest impact. Ability to propose data-driven product features or improvements proactively.

• Publications/Patents – Any publications, Kaggle competition results, or patented techniques in relevant areas of machine learning are a plus (demonstrating thought leadership and expertise depth).