ML Ops Infrastructure Engineer at Deepgram

Department: Engineering

Compensation

$160,000 – $220,000/yr

Setup: Remote
Type: Full-time
Level: mid
Posted: Apr 6, 2026

Description

Deepgram is hiring an ML Ops Infrastructure Engineer to build and maintain the pipelines, deployment systems, testing infrastructure, monitoring, observability, and automated retraining systems that move voice AI models from research to production at scale. The role requires 4+ years of MLOps, DevOps, or infrastructure engineering experience, strong Python and CI/CD skills, and hands-on experience with Docker, Kubernetes, and production ML model serving.

Required Skills

Python
CI/CD
Docker
Kubernetes
Model serving
Containerization
Observability

Additional Information

Required Previous Experiences: 4+ years of MLOps, DevOps, or infrastructure engineering experience focused on ML systems
Python proficiency and experience building automation and tooling for ML workflows
Deep experience with CI/CD systems and software and model delivery pipelines
Hands-on experience with Docker and Kubernetes for containerized workload management
Experience deploying and serving ML models in production environments
Familiarity with model evaluation, validation, and quality assurance processes
Understanding of monitoring and observability principles for ML systems
Preferred Qualifications: Experience with NVIDIA Triton Inference Server, TensorRT, or ONNX Runtime
Background in speech, audio, or real-time media ML systems
Experience with Terraform or Pulumi
Experience with Prometheus, Grafana, Datadog, or similar monitoring stacks
Familiarity with GPU-accelerated inference optimization and profiling
Experience with feature stores, data versioning, or ML metadata management
Knowledge of canary deployment strategies and progressive delivery for ML models
Translation Company Name: Deepgram

About Deepgram

Deepgram

AI speech recognition technologySan Francisco, CA, US51-200

Deepgram is a foundational Voice AI platform for developers, offering unified APIs for Speech-to-Text (STT), Text-to-Speech (TTS), and autonomous Voice Agent orchestration. Available as a managed API (US, EU, and Australia endpoints), in-VPC, or self-hosted.