# ML Ops Infrastructure Engineer

Hiring organization: [Deepgram](https://career.thegoodapps.co/organizations/deepgram)

Canonical page: https://career.thegoodapps.co/jobs/c3a27a22-7d2d-4e9b-84c2-b1a42c374195

Listed on Deepgram's own careers site. Applications go to them directly.

- Seniority: Mid
- Location: USA | Remote
- Remote: yes
- Salary: 160000 – 220000 USD per year

## Summary

This role bridges research and production at an AI voice platform, building the infrastructure that takes experimental models through CI/CD pipelines to serving millions of API requests. You'll own deployment automation, monitoring, and testing systems for machine learning models at scale.

_Our summary, not Deepgram's wording._

## Skills named

CI/CD, Datadog, Docker, Grafana, Kubernetes, NVIDIA Triton Inference Server, Prometheus, Pulumi, Python, Terraform

## Required

- 4+ years of MLOps, DevOps, or infrastructure engineering experience focused on ML systems
- Proficiency in Python for ML automation and tooling
- Deep experience with CI/CD systems for software and model delivery
- Hands-on Docker and Kubernetes for containerized workloads
- Production ML model deployment and serving experience
- Understanding of model evaluation and quality assurance processes
- Knowledge of monitoring and observability for ML systems
- Strong problem-solving with bias toward automation

## Nice to have

- Experience with model serving frameworks like NVIDIA Triton, TensorRT, or ONNX Runtime
- Background in speech, audio, or real-time media ML systems
- Infrastructure as Code tools such as Terraform or Pulumi
- Hands-on monitoring stacks like Prometheus, Grafana, or Datadog
- GPU-accelerated inference optimization and profiling
- Feature stores, data versioning, or ML metadata management
- Canary deployment and progressive delivery strategies for models

Apply on Deepgram's site: https://jobs.ashbyhq.com/Deepgram/7ced4c1f-4126-44fe-9cf1-da427a9e4e3e/application