ML Ops Infrastructure Engineer: Scale AI Models

Deepgram; United States; Remote; USD 140,000 - 180,000; Full time

Benefits offered by this job

Medical, dental, vision benefits

Unlimited PTO

401(k) plan with company match

Learning / Education stipend

Job summary

A cutting-edge AI company is seeking an experienced ML Ops Infrastructure Engineer to bridge research and production. This role focuses on designing and building CI/CD pipelines and deploying ML models for real-time applications. With a strong emphasis on automation, monitoring, and collaboration, the ideal candidate has significant experience in MLOps and proficiency in Python. Join our fast-paced environment where innovation is key to delivering exceptional AI solutions.

Qualifications

• Over 4 years of experience in MLOps, DevOps, or infrastructure engineering.
• Strong proficiency in Python and building automation for ML workflows.
• Hands-on experience with CI/CD systems and Docker/Kubernetes.

Responsibilities

• Design and build CI/CD pipelines for ML model deployment.
• Implement monitoring for model performance in production.
• Collaborate with research engineers to define model quality gates.

Skills

Python

CI/CD systems

Docker

Kubernetes

Automation

Problem-solving

Education

4+ years in MLOps, DevOps, or infrastructure engineering

Tools

NVIDIA Triton Inference Server

Terraform

Prometheus

Grafana

Datadog

Job description

A cutting-edge AI company is seeking an experienced ML Ops Infrastructure Engineer to bridge research and production. This role focuses on designing and building CI/CD pipelines and deploying ML models for real-time applications. With a strong emphasis on automation, monitoring, and collaboration, the ideal candidate has significant experience in MLOps and proficiency in Python. Join our fast-paced environment where innovation is key to delivering exceptional AI solutions.