ML Ops Infrastructure Engineer

Deepgram

About The Position

Getting a model from a research notebook to a production API serving millions of requests is one of the hardest problems in AI. As an ML Ops Infrastructure Engineer at Deepgram, you will own the critical bridge between research and production -- building the pipelines, deployment systems, and testing infrastructure that take models from experimental to battle-tested at scale. Your work ensures that every model improvement our research team makes can be safely, quickly, and reliably delivered to the customers who depend on Deepgram's APIs for real-time voice AI.

Requirements

4+ years of experience in MLOps, DevOps, or infrastructure engineering with a focus on ML systems
Strong proficiency in Python and experience building automation and tooling for ML workflows
Deep experience with CI/CD systems and building pipelines for software and model delivery
Hands-on experience with Docker and Kubernetes for containerized workload management
Practical experience deploying and serving ML models in production environments
Familiarity with model evaluation, validation, and quality assurance processes
Understanding of monitoring and observability principles as applied to ML systems
Strong problem-solving skills and a bias toward automation over manual processes

Nice To Haves

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
Experience with Infrastructure as Code tools such as Terraform or Pulumi
Hands-on experience with monitoring and observability stacks (Prometheus, Grafana, Datadog, or similar)
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

Responsibilities

Design and build CI/CD pipelines specifically tailored for ML model development, validation, and deployment
Architect and maintain model deployment pipelines that move models from research environments through staging to production with confidence
Build A/B testing infrastructure that enables controlled rollouts of new models and measures real-world performance impact
Implement comprehensive monitoring for model performance in production -- accuracy metrics, latency, drift detection, and regression alerts
Develop automated retraining pipelines that trigger on data changes, performance degradation, or scheduled cadences
Create and maintain build and test environments that mirror production, giving researchers high-fidelity feedback before deployment
Establish model versioning, artifact management, and rollback capabilities to ensure safe and reproducible deployments
Collaborate with research engineers to define and enforce model quality gates before production promotion
Build observability dashboards that give the team real-time insight into model health across all environments
Optimize model serving infrastructure for latency, throughput, and cost efficiency