Deepgram
ML Ops Infrastructure Engineer
$160K–$220K
USA - Remote · Remote · Full-time · Posted Apr 6, 2026
- Experience
- 4+ years in MLOps, DevOps, or infrastructure engineering with a focus on ML systems.
About the job
Build and operate the pipelines, deployment systems, testing infrastructure, and monitoring that move ML models from research into reliable production APIs.
What you'll do
- Build CI/CD, model deployment, automated retraining, and testing pipelines.
- Implement model evaluation, A/B testing, monitoring, versioning, and rollback capabilities.
- Optimize model-serving infrastructure for latency, throughput, and cost.
What they ask for
- 4+ years of experience in MLOps, DevOps, or infrastructure engineering focused on ML systems.
- Strong proficiency in Python and experience building automation and tooling for ML workflows.
- Deep experience with CI/CD systems and pipelines for software and model delivery.
- Hands-on experience with Docker and Kubernetes, and deploying and serving ML models in production.
Nice to have
- Experience with model-serving frameworks such as NVIDIA Triton Inference Server, TensorRT, or ONNX Runtime.
- Background in speech, audio, or real-time media ML systems.
Pay
$160K – $220K (USD, base salary); Offers Equity; Offers Bonus
Tools
Python, Docker, Kubernetes, NVIDIA Triton Inference Server, TensorRT, ONNX Runtime, Terraform, Pulumi
AI focus
Operationalize, deploy, monitor, test, and optimize ML models in production; the company also expects employees to actively use and experiment with advanced AI tools in their work.
Model-written summary · the original posting is authoritative