WHY SOCURE?

At Socure, we’re on a mission—to verify 100% of good identities in real time and eliminate identity fraud from the internet.
Using predictive analytics and advanced machine learning trained on billions of signals to power RiskOS, Socure has created the most accurate identity verification and fraud prevention platform in the world. Trusted by thousands of leading organizations—from top banks and fintechs to government agencies—we solve real, high-impact problems at scale. Come join us!

PREFERRED QUALIFICATIONS

• Experience building internal ML platform services or self-service tooling for model deployment and monitoring.
• Understanding of model optimization techniques (e.g., TorchScript, ONNX, quantization, batching).
• Experience with feature stores, real-time feature serving, or caching systems for ML workloads.
• Background in deploying ML models into high-availability, mission-critical environments.
  Please note that Socure cannot provide sponsorship now or in the future for this opening.
  Socure is an equal opportunity employer and values diversity of all kinds at our company. We do not discriminate based on race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.

ABOUT THE ROLE

As a Senior Software Engineer on Socure’s AI Platform team, you’ll design and build infrastructure that supports model training, validation, deployment, and serving at scale. You will work with modern AWS-native technologies, focusing on low-latency microservices, automated pipelines, and robust deployment workflows to enable safe and efficient delivery of machine learning models into production.
This role is ideal for someone who enjoys building platforms and tools that abstract complexity for ML and data science teams, and who thrives in fast-paced environments where engineering excellence and reliability are paramount.

WHAT YOU’LL DO

• Build and maintain scalable systems and infrastructure for deploying and serving ML models.
• Design low-latency, fault-tolerant model inference systems using Amazon SageMaker.
• Implement safe deployment strategies like blue/green deployments and rollbacks.
• Create and manage CI/CD pipelines for ML workflows.
• Monitor model performance and system health using AWS observability tools (e.g., CloudWatch).
• Develop internal tools and APIs to help ML teams deploy and monitor models easily.
• Collaborate with ML engineers, data scientists, and DevOps to productionize new models.
• Participate in code reviews, system design, and platform roadmap discussions.
• Continuously improve deployment reliability, speed, and usability of the ML platform.