Senior Machine Learning Modeler, Advanced Insights & Modeling

<p>Block is one company built from many blocks, all united by the same purpose of economic empowerment. The blocks that form our foundational teams — People, Finance, Counsel, Hardware, Information Security, Platform Infrastructure Engineering, and more — provide support and guidance at the corporate level. They work across business groups and around the globe, spanning time zones and disciplines to develop inclusive People policies, forecast finances, give legal counsel, safeguard systems, nurture new initiatives, and more. Every challenge creates possibilities, and we need different perspectives to see them all. Bring yours to Block.</p> <p><strong>The Role</strong></p> <p>We're looking for a Senior Machine Learning Modeler to pioneer the design of intelligent systems that power the future of decision-making across Block—spanning Cash App, Square, and Corporate domains such as Treasury, Cost, and Accounting.</p> <p>You'll lead the architecture and delivery of AI-driven, self-adaptive models that forecast, reason, and act—shaping how Block allocates resources, scales growth, and plans for the future. This means going beyond traditional modeling: building autonomous ML workflows, graph-based retrieval systems (GraphRAG), and agentic orchestration frameworks (MCP and beyond) that make insights discoverable, explainable, and actionable across the company.</p> <p>As a senior technical leader, you'll work across business and engineering boundaries—collaborating with Data Science, Forecasting Analytics, and Finance—to design scalable, trustworthy AI systems that turn complexity into clarity. Your work will set the standard for how Block brings together machine learning, automation, and intelligent decisioning to drive long-term business impact.</p> <p><strong>You Will</strong></p> <ul> <li>Lead design and implementation of forecasting, financial, and cost modeling systems that inform company-wide decisions.</li> <li>Develop scalable ML architectures and pipelines for training, serving, and monitoring predictive models.</li> <li>Build and extend AI tools for model explainability and interpretability, making predictions accessible to Finance, Analytics, and Product teams.</li> <li>Partner with Data Science to operationalize research models, ensuring performance, reliability, and reproducibility.</li> <li>Collaborate with Forecasting Analytics and Corporate Finance teams to deliver insights that guide resource allocation and financial planning.</li> <li>Define technical standards, best practices, and frameworks for applied ML development across business lines.</li> </ul> <p><strong>You Have</strong></p> <ul> <li>8+ years of experience in machine learning or software engineering, with proven experience leading large-scale ML projects.</li> <li>Deep expertise in forecasting, predictive modeling, and value estimation, including statistical and ML-based methods.</li> <li>Advanced proficiency in Python, and experience with libraries such as scikit-learn, XGBoost, LightGBM, and pandas/numpy.</li> <li>Strong experience building end-to-end ML pipelines, leveraging tools like Airflow, Spark, BigQuery, or equivalent systems.</li> <li>Demonstrated success in designing systems that support explainability, reproducibility, and operational reliability.</li> <li>Strong understanding of data modeling, feature engineering, and model evaluation in production contexts.</li> <li>Experience mentoring engineers and shaping team-wide technical direction.</li> <li>Experience with forecasting frameworks (e.g., Prophet, statsmodels, or custom time-series methods).</li> <li>Background in financial modeling, planning, or customer lifetime value prediction.</li> <li>Experience building automated or interactive explainability systems for ML-driven forecasts.</li> </ul> <p> </p> <p>We're working to build a more inclusive economy where our customers have equal access to opportunity, and we strive to live by these same values in building our workplace. Block is an eq ... (truncated, view full listing at source)