Staff ML Architect - Payments AI & Risk

Payabli; Miami (FL); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Stock options

Flexible PTO

Parental leave

Medical, dental, & vision insurance

401K / HSA

Job summary

Payabli is hiring a Staff Machine Learning Engineer in Miami to lead the technical direction for its ML portfolio. You will shape models that optimize risk reviews, merchant scoring, and payments operations, while building new models across the payments lifecycle.

You'll partner with product, engineering, and risk teams to define what “good” looks like for ML, establish monitoring and experimentation, and mentor the next generation of ML engineers.

Qualifications

• 8+ years of ML engineering experience with 4+ years shipping production models.
• Own modeling architecture and production deployments end-to-end.
• Broad model types and problem framing across domains.
• Experience taking models from prototype to production and monitoring.
• Explainability, latency, and regulatory considerations in modeling.

Responsibilities

• Set the technical direction for Payabli's ML portfolio across lifecycle stages.
• Establish experimentation workflows, monitoring, drift detection, and benchmarking.
• Translate payments problems into scoped modeling opportunities with business impact.
• Mentor engineers, set best practices, and raise technical bar.
• Partner with product, engineering, and risk teams to own the ML roadmap.

Skills

ML engineering

Production models

Model monitoring

Drift detection

Experimentation

Feature development

Retraining

MLOps tooling

Stakeholder communication

Tools

AWS SageMaker

Feature stores

Training pipelines

Inference pipelines

MLOps tooling

Job description

Payabli is hiring a Staff Machine Learning Engineer in Miami to lead the technical direction for its ML portfolio. You will shape models that optimize risk reviews, merchant scoring, and payments operations, while building new models across the payments lifecycle.

You'll partner with product, engineering, and risk teams to define what “good” looks like for ML, establish monitoring and experimentation, and mentor the next generation of ML engineers.