ML Ops Infrastructure Engineer
Core
Build CI/CD pipelines, deployment systems, and testing infrastructure to move ML models from research notebooks to production APIs serving millions of requests.
Role type
Senior IC ML Ops Infrastructure Engineer
Builds
Production-grade ML model serving pipelines, A/B testing infrastructure, automated retraining systems, and observability dashboards for voice AI models.
Domain
Voice AI / Speech-to-Text / Real-time media systems
Deliverable
production ML models
Required skills
Python, CI/CD pipeline design, Docker, Kubernetes, ML model deployment, model evaluation, monitoring and observability, automation
Preferred skills
NVIDIA Triton Inference Server, TensorRT, ONNX Runtime, Infrastructure as Code (Terraform/Pulumi), GPU inference optimization, feature stores, canary deployment strategies
Technologies
Python, Docker, Kubernetes, Terraform, Pulumi, Prometheus, Grafana, Datadog, NVIDIA Triton, TensorRT, ONNX Runtime
Responsibilities
Design and build CI/CD pipelines for ML model development and deployment; Architect model deployment pipelines from research to production; Build A/B testing infrastructure for controlled model rollouts; Implement monitoring for model performance, accuracy, latency, and drift; Develop automated retraining pipelines; Create build and test environments mirroring production; Establish model versioning and rollback capabilities; Build observability dashboards for model health; Optimize model serving infrastructure for latency and cost.
Seniority
Senior, hands-on IC
