Senior Machine Learning Engineer, Risk Signals & Controls

<p><strong>The Role</strong></p> <p>The Risk Signals and Controls team's mission is to power Block's risk decisions with trusted signals and lean, effective models built on evolving data. We do that by building efficient tools and workflows to accelerate fraud detection and model effectiveness evaluating thousands of transactions per second in real time. We closely collaborate with ML Modellers and Software Engineers from across Block to optimize the signal lifecycle to improve signal quality, reduce noise, and accelerate time-to-insight. We're also excited to explore new directions with the team to continue pushing the boundaries of what's possible.</p> <p><strong>You Will</strong></p> <ul> <li>Design, build, and maintain data pipelines to ingest third parties and Block data to enhance our feature store and modeling capabilities.</li> <li>Design elegant ML pipelines and services, prototype new approaches, and productionize solutions at scale.</li> <li>Build tooling to help maintain our features and models, gaining efficiencies in fraud detection.</li> <li>Work hand-in-hand with ML Modelers to identify and integrate new data sources, heuristics and models.</li> <li>Solve challenging technical problems at scale, collaborating with colleagues located across the globe</li> <li>Apply ML and engineering best practices to shape how Block develops, tests, and maintains ML-platform solutions.</li> <li>Ensure data quality and completeness through automated validation, monitoring, and alerting.</li> <li>Own your solutions from design through to operation: we all share the pager!</li> </ul> <p><strong>You Have</strong></p> <ul> <li>12+ years of experience in software development and demonstrated technical initiative and leadership on previous machine learning projects.</li> <li>A proven ability to shape how teams effectively adopt and evolve AI practices; driving adoption of AI-first workflows by coaching leaders, identifying scalable use cases, and embedding quality and accountability in team norms.</li> <li>Work autonomously in a fast paced, ambiguous and unpredictable environment</li> <li>Natural curiosity eagerness to learn</li> <li>Show the ability to take initiative, lead, and drive creative solutions in cross-team contexts.</li> <li>A strong interest in owning your solutions, maintaining and fixing them as necessary</li> <li>Communicate via clear and concise writing to facilitate asynchronous collaboration across multiple time zones</li> <li>Reason about complex, distributed systems at high scale</li> <li>Proficiency in machine learning techniques, experimental design and data engineering</li> <li>Strong programming skills in languages such as Kotlin, Python, TensorFlow, or PyTorch</li> </ul> <p><strong>Technologies We Use and Teach</strong></p> <p>We value general engineering skill and versatility over existing domain knowledge, but here's a sample of what we currently use:</p> <ul> <li>Python, Java and Kotlin</li> <li>HTTP, JSON, gRPC, Protocol Buffers</li> <li>AWS, Databricks, and Kubernetes</li> <li>MySQL, DynamoDB, Kafka, Spark</li> <li>Prefect, Airflow</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 a proud equal opportunity employer. We work hard to evaluate all employees and job applicants consistently, based solely on the core competencies required of the role at hand, and without regard to any legally protected class. We believe in being fair, and are committed to an inclusive interview experience, including providing reasonable accommodations to disabled applicants throughout the recruitment process. We encourage applicants to share any needed accommodations with their recruiter, who will treat these requests as confidentially as possible. <strong><em>Want to learn more about what we're doing to build an inclusive workplace? Check out our <a href="https://block.xyz/n ... (truncated, view full listing at source)