Staff ML Platform Engineer - Production AI Infra (Remote)

creditacceptance; United States; Hybrid; USD 154,000 - 226,000; Full time

Benefits offered by this job

401(K) match

Adoption assistance

Parental leave

Tuition reimbursement

Comprehensive medical/dental/vision

Job summary

Credit Acceptance is seeking an experienced ML/AI platform engineer to own the deployment path and production lifecycle for all ML/GenAI models. You will manage training/inference pipelines, model registry, and serving endpoints, ensuring reliability and observability in production.

This role emphasizes operations and infrastructure over modeling, with a focus on uptime, safe deployments, and cost efficiency across the platform.

Qualifications

• Bachelor's degree or higher in a technical field with 7+ years of relevant experience.
• 5+ years building and operating production ML/AI systems with ownership of pipelines or serving infrastructure.
• Strong Python and SQL with production-grade engineering practices.

Responsibilities

• Own end-to-end deployment path for ML/GenAI models including training/inference pipelines and model registry.
• Monitor production models with health, latency, throughput, and auto-scaling.
• Operate gateway routing for agents and ensure least-privilege tool access.
• Evaluate agents in production with online scoring and drift detection.
• Develop observability and evaluation substrate and data contracts.
• Manage platform unit economics and cost per inference.

Skills

Python

SQL

Cloud platforms

Monitoring/observability

CI/CD for ML

Model serving

Data engineering

Education

Bachelor's degree in Computer Science/Engineering/Statistics

Master's degree in related field (optional)

Tools

MLflow

Docker

Kubernetes

Job description

Credit Acceptance is seeking an experienced ML/AI platform engineer to own the deployment path and production lifecycle for all ML/GenAI models. You will manage training/inference pipelines, model registry, and serving endpoints, ensuring reliability and observability in production.

This role emphasizes operations and infrastructure over modeling, with a focus on uptime, safe deployments, and cost efficiency across the platform.