Jobs at Signifyd

Leads and develops an engineering team building, deploying, and operating machine-learning models and services for fraud prevention. Owns roadmap delivery, technical decisions, reliability, testing, monitoring, and stakeholder communication. Partners with data scientists, ML engineers, product, risk, and engineering teams. Drives responsible AI-tool adoption, recruits and coaches engineers, manages priorities, and ensures scalable, high-quality production systems.

Build and deploy production machine learning models and fraud decisioning tools. Partner with business teams to identify performance gaps, automate repetitive work, run experiments, and optimize transaction-risk strategies. Write production and analytical Python code, use SQL and distributed data platforms such as Spark, Databricks, and GCP, and communicate findings to technical and business audiences. Participate in code reviews, peer collaboration, and an on-call weekend rotation approximately six times annually.

Build and deploy production machine learning models and fraud decisioning tools for e-commerce transactions. Partner with business teams to improve decisioning performance, automate manual processes, run experiments, and balance model complexity with performance. Write and review Python and SQL code, work with distributed data pipelines using Spark, Databricks, and GCP, communicate findings to technical and business audiences, and participate in an on-call weekend rotation.

Generate qualified pipeline for high-value e-commerce accounts through targeted research, personalized outreach, discovery calls, and collaboration with strategic sellers. Manage mid-funnel opportunities, maintain accurate CRM records, coordinate with Marketing, Sales Operations, and Partnerships, report on sales metrics, and contribute to sales process improvements. The role requires strong communication, organization, CRM proficiency, and understanding of longer sales cycles.

Lead end-to-end ML projects for fraud detection: develop, deploy, monitor, and iterate production models and experimentation frameworks. Improve model performance, build scalable ML pipelines, collaborate with Product/Engineering/Risk, and champion testing, documentation, and model-monitoring best practices to ensure robust, high-impact solutions.

Lead design, implementation, and operation of Signifyd's GCP/Kubernetes cloud platform. Architect scalable, secure infrastructure, embed AI-driven automation, own SLOs and incident response, improve developer experience via CI/CD/GitOps tooling, mentor engineers, manage cloud capacity/FinOps, and build observability and security into the platform.

Lead and grow a machine learning engineering team responsible for fraud and risk models. Manage experimentation portfolios, balance research with delivery, evaluate model performance rigorously, and guide work through production release. Partner with Risk, platform, and infrastructure teams to set priorities, improve training and experimentation systems, communicate results, and make autonomous roadmap decisions. The role is a hands-on player-coach requiring technical depth, people leadership, strong communication, and comfort operating under uncertainty.

Lead and grow a distributed ML engineering team that runs experiments, ships production models, and partners with Risk and platform teams. Balance research bets and delivery, enforce rigorous evaluation and reproducibility, mentor engineers, own roadmap trade-offs, and represent results to stakeholders while improving model performance and production reliability.

The Machine Learning Engineer II builds production ML models to detect fraud, collaborates on engineering teams, and improves the commerce protection platform.

Lead design and delivery of the public-facing API platform and ingestion services. Build scalable, reliable real-time distributed systems, collaborate with product and data teams, review designs and code, address technical debt, take operational ownership using observability tools, and mentor engineers.