ML Ops Infrastructure Engineer

📋 Description

• • 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.
• • You will design and build CI/CD pipelines for ML model development, validation, and deployment; architect model deployment pipelines from research to production; build A/B testing infrastructure; implement monitoring for model performance; develop automated retraining pipelines; create build and test environments mirroring production; establish model versioning and rollback capabilities; collaborate with research engineers on quality gates; build observability dashboards; and optimize model serving infrastructure for latency, throughput, and cost efficiency.
• • Deepgram is the leading platform underpinning the emerging trillion-dollar Voice AI economy, providing real-time APIs for speech-to-text, text-to-speech, and voice agents at scale, serving over 200,000 developers and 1,300+ organizations including Twilio, Cloudflare, and Jack in the Box.
• • You will work in an AI-first environment where rapid change, experimentation, and continuous learning are expected, and where your infrastructure work directly enables research breakthroughs to reach customers reliably and efficiently.