ML Engineer
2 - 5 years
San Francisco, CA
Full-time
Remote
1 month ago
About the role
Please note no 3rd party agencies / C2C / No Sponsorship available at this time.
Our CLIENT is re-writing the risk model for the non-QM mortgage market -combining data analytics, proprietary risk intelligence, and Loan Defect Insurance to turn mortgage manufacturing risk into quantifiable, insurable outcomes for lenders, investors, and RMBS issuers. Our Client is the analytical engine powering this platform, built on neural network triage, hazard-based pricing, and AI-driven defect detection. The ML Engineer owns the layer between a trained model and a trusted production output - responsible for automated scoring pipelines, audit logging, API delivery, and the monitoring systems that catch degradation before it affects real insurance decisions
In this role you will:
· Productize all CLIENT models -automated scoring pipelines delivering triage, hazard pricing, defect detection, fraud, and compliance outputs without manual intervention
· Design and implement production model monitoring -tracking performance, detecting data drift and output distribution shift, alerting before degradation affects downstream decisions
· Own the audit logging layer -all model inputs, feature values, and scores captured, timestamped, and immutably stored for every scoring event
· Build and maintain the API infrastructure delivering CLIENT's outputs to internal systems and external counterparties -versioned, documented, and meeting institutional SLA requirements
· Support audit requests by producing reproducible scoring traces for any historical loan or pool
· Own the model deployment workflow: packaging, versioning, staging validation, and production promotion gates
The Ideal Candidate:
· Treats production reliability and audit traceability as first-class engineering concerns
· Comfortable owning systems end-to-end with minimal process overhead
· Proactively monitors for problems rather than waiting for them to surface
Basic Qualifications:
· 4+ years of ML engineering or software engineering with at least 2 years productizing ML models
· Automated ML scoring pipelines, deployment workflows, and CI/CD for ML
· Model monitoring -drift detection, performance tracking, and alerting
· Python and API development (FastAPI or equivalent)
Preferred Qualifications:
· Models productized in financial services or insurance subject to external audit
· Model monitoring tooling: Evidently AI, Arize, WhyLabs, or equivalent
· APIs serving model outputs to institutional counterparties with formal SLA requirements
· Real-time or near-real-time scoring for loan-level risk decisioning
Tech: Python · FastAPI · MLflow · Docker / Kubernetes · AWS Lambda or equivalent · PostgreSQL (audit log) · Git / CI-CD
Our CLIENT is re-writing the risk model for the non-QM mortgage market -combining data analytics, proprietary risk intelligence, and Loan Defect Insurance to turn mortgage manufacturing risk into quantifiable, insurable outcomes for lenders, investors, and RMBS issuers. Our Client is the analytical engine powering this platform, built on neural network triage, hazard-based pricing, and AI-driven defect detection. The ML Engineer owns the layer between a trained model and a trusted production output - responsible for automated scoring pipelines, audit logging, API delivery, and the monitoring systems that catch degradation before it affects real insurance decisions
In this role you will:
· Productize all CLIENT models -automated scoring pipelines delivering triage, hazard pricing, defect detection, fraud, and compliance outputs without manual intervention
· Design and implement production model monitoring -tracking performance, detecting data drift and output distribution shift, alerting before degradation affects downstream decisions
· Own the audit logging layer -all model inputs, feature values, and scores captured, timestamped, and immutably stored for every scoring event
· Build and maintain the API infrastructure delivering CLIENT's outputs to internal systems and external counterparties -versioned, documented, and meeting institutional SLA requirements
· Support audit requests by producing reproducible scoring traces for any historical loan or pool
· Own the model deployment workflow: packaging, versioning, staging validation, and production promotion gates
The Ideal Candidate:
· Treats production reliability and audit traceability as first-class engineering concerns
· Comfortable owning systems end-to-end with minimal process overhead
· Proactively monitors for problems rather than waiting for them to surface
Basic Qualifications:
· 4+ years of ML engineering or software engineering with at least 2 years productizing ML models
· Automated ML scoring pipelines, deployment workflows, and CI/CD for ML
· Model monitoring -drift detection, performance tracking, and alerting
· Python and API development (FastAPI or equivalent)
Preferred Qualifications:
· Models productized in financial services or insurance subject to external audit
· Model monitoring tooling: Evidently AI, Arize, WhyLabs, or equivalent
· APIs serving model outputs to institutional counterparties with formal SLA requirements
· Real-time or near-real-time scoring for loan-level risk decisioning
Tech: Python · FastAPI · MLflow · Docker / Kubernetes · AWS Lambda or equivalent · PostgreSQL (audit log) · Git / CI-CD
Skills
Staffing and Recruiting