Remote ML Ops Engineer for Production-Scale AI

Bazeta; United States; Remote; USD 140,000 - 240,000; Full time

Job summary

Deepgram is seeking an ML Ops Infrastructure Engineer to bridge research and production, building end-to-end pipelines, deployment systems, and testing infrastructure that scale real-time models to millions of requests. You will own model versioning, observability, and cost-efficient serving, ensuring reliable delivery of improvements to customers.

You'll design and maintain CI/CD pipelines tailored for ML workflows, implement AB testing, automated retraining, and robust monitoring across

Qualifications

• 4+ years in MLOps, DevOps, or ML infra.
• Strong Python and automation for ML workflows.
• CI/CD experience for model delivery.
• Docker and Kubernetes for containerized workloads.
• Experience deploying ML models in production.

Responsibilities

• Design and build ML CI/CD pipelines from research to deployment.
• Maintain model deployment pipelines across staging to production.
• Build AB testing infra for controlled model rollouts.
• Implement monitoring for model performance and drift.
• Develop automated retraining pipelines triggered by data changes.
• Create production-like build/test environments for researchers.
• Model versioning, artifact management, rollback capabilities.
• Collaborate with researchers to enforce model quality gates.
• Build dashboards for real-time health across environments.
• Optimize serving infra for latency, throughput, cost.

Skills

Python

CI/CD

Automation

Model deployment

Monitoring

AB testing

MLOps

DevOps

Troubleshooting

Latency optimisation

Tools

Docker

Kubernetes

Terraform

Pulumi

Prometheus

Grafana

Datadog

NVIDIA Triton

ONNX Runtime

Job description

Deepgram is seeking an ML Ops Infrastructure Engineer to bridge research and production, building end-to-end pipelines, deployment systems, and testing infrastructure that scale real-time models to millions of requests. You will own model versioning, observability, and cost-efficient serving, ensuring reliable delivery of improvements to customers.

You'll design and maintain CI/CD pipelines tailored for ML workflows, implement AB testing, automated retraining, and robust monitoring across