Latest AI JobsBrowse Jobs
Deepgram logo

ML Ops Infrastructure Engineer

DeepgramUSA - RemoteEngineering
Apply on company site
Salary
$160K - $220K USD
Job type
Full-time
Work mode
Remote
Posted
6 Apr 2026
Status
Open · checked 7d ago

About this role

Deepgram is seeking an ML Ops Infrastructure Engineer to join its remote engineering team in the USA. This full-time position is ideal for an infrastructure professional who wants to bridge the gap between AI research and production systems.

Role Overview

Moving an artificial intelligence model from an experimental research notebook into a high-performance production API is a significant technical challenge. In this role, the engineer owns the essential bridge between research and live operations, constructing the pipelines, deployment architectures, and testing systems required to scale models. The work directly enables continuous model enhancements from the research team to reach customers relying on real-time voice artificial intelligence APIs securely and efficiently. Success in this position requires an AI-first mindset, adaptability, and comfort with rapidly evolving daily responsibilities in a fast-paced environment.

Key Responsibilities

Design and construct continuous integration and continuous delivery pipelines specifically customized for artificial intelligence model creation, testing, and release.
Architect and maintain deployment pathways that transition models smoothly from research stages into staging and live production.
Construct A/B testing frameworks allowing controlled rollouts of fresh models alongside real-world performance tracking.
Deploy thorough monitoring systems for active production models to track latency, accuracy metrics, regression alerts, and drift detection.
Develop automated retraining workflows activated by scheduled cadences, data updates, or drops in performance.
Build and maintain testing and build environments replicating production to supply researchers with accurate feedback.
Establish robust model versioning, rollback features, and artifact management to guarantee reproducible deployments.
Partner alongside research engineers to create and enforce strict quality gates before models reach production.
Construct observability dashboards providing live insights regarding model health across every environment.
Fine-tune model serving infrastructure to maximize throughput, minimize latency, and improve cost efficiency.

Requirements

Minimum of 4 years of professional background working in infrastructure engineering, DevOps, or MLOps with a concentration on machine learning platforms.
Advanced proficiency utilizing Python alongside experience creating automation tools and workflows for machine learning.
Extensive background implementing continuous integration and delivery systems for software and model releases.
Practical, hands-on experience using Kubernetes and Docker to manage containerized workloads.
Direct operational background deploying and serving machine learning models within live production settings.
Familiarity with quality assurance, validation, and model evaluation procedures.
Solid grasp of observability and monitoring concepts tailored toward machine learning architectures.
Demonstrated analytical problem-solving abilities paired with a strong preference for automation over manual tasks.

Nice to Have

Practical experience utilizing model serving frameworks such as ONNX Runtime, TensorRT, or NVIDIA Triton Inference Server.
Prior background working with real-time media, audio, or speech machine learning platforms.
Professional familiarity utilizing Infrastructure as Code technologies including Pulumi or Terraform.
Direct experience working with monitoring tools and observability stacks like Datadog, Grafana, Prometheus, or comparable solutions.
Familiarity profiling and optimizing GPU-accelerated inference.
Background handling feature stores, data versioning, or metadata management for machine learning.
Knowledge regarding progressive delivery and canary deployment techniques for artificial intelligence models.

Skills and Tools

Python
Kubernetes
Docker
MLOps
Terraform
CI/CD Pipelines
Model Serving Frameworks
Monitoring and Observability Stacks

Salary and Benefits

Annual Salary Range: $160,000 to $220,000 USD

About the Company

Deepgram operates as the leading platform powering the trillion-dollar voice artificial intelligence economy. The organization offers real-time APIs for text-to-speech, speech-to-text, and the creation of production-scale voice agents. Over 1,300 organizations and 200,000 developers utilize offerings powered by Deepgram, including notable enterprises like Twilio, Cloudflare, and Vapi. The company provides voice-native foundation models via self-hosted software, on-premises setups, and cloud APIs.

How to Apply

Interested candidates should visit the official Deepgram careers page to submit an application for this remote position. All legitimate recruitment communications originate exclusively from an @deepgram.com email address.

Skills and tech stack

PythonKubernetesDockerMLOpsTerraform

Questions candidates ask

What is the salary range for the ML Ops Infrastructure Engineer role?

The annual salary for this position ranges from $160,000 to $220,000 USD.

Is this job remote?

Yes, this position is designated as USA - Remote.

What level of experience is required?

Candidates must have at least 4 years of professional experience in MLOps, DevOps, or infrastructure engineering with a strong focus on machine learning systems.

What core technical skills are required?

Required technical competencies include Python, Kubernetes, Docker, MLOps, CI/CD pipeline building, model deployment, monitoring, and infrastructure automation.

What is Deepgram's operating rhythm regarding AI?

Deepgram expects an AI-first mindset where employees actively experiment with advanced artificial intelligence tools, build them into everyday workflows, and adapt quickly to rapid changes.

How should I apply for this position?

Candidates should apply directly through the official Deepgram careers page and ensure all recruitment correspondence comes from an official @deepgram.com email address.

Ready to apply?

The application is on the official Deepgram careers page.

Apply on company site