ML Ops Infrastructure Engineer
Deepgram · USA - Remote
About this role
## ML Ops Infrastructure Engineer ### Company Overview Deepgram is the leading platform underpinning the Voice AI economy, providing real-time APIs for speech-to-text (STT), text-to-speech (TTS), and production-grade voice agents at scale. With voice-native foundation models available via cloud APIs or self-hosted/on-prem software, Deepgram delivers accuracy, low latency, and cost efficiency. ### Operating Rhythm Deepgram is **AI-first**: team members are expected to actively use, experiment with, and even build AI tools into their everyday workflows. The pace is fast—change evolves quickly—so this role is best for people who enjoy adapting, learning continuously, and operationalizing new capabilities. ### The Opportunity As an **ML Ops Infrastructure Engineer**, you’ll own the bridge between research and production—building pipelines, deployment systems, and testing infrastructure that take models from experimental to battle-tested at scale. Your work ensures model improvements can be delivered safely, quickly, and reliably to customers using Deepgram’s real-time voice APIs. ### What You’ll Do - Design and build **CI/CD pipelines** tailored for ML model development, validation, and deployment - Architect and maintain **model deployment pipelines** from research → staging → production - Build **A/B testing infrastructure** for controlled rollouts and real-world performance measurement - Implement **production monitoring** (accuracy metrics, latency, drift detection, regression alerts) - Develop **automated retraining pipelines** triggered by data changes, performance degradation, or schedules - Create and maintain **build/test environments** that mirror production for high-fidelity feedback - Establish **model versioning, artifact management, and rollback** capabilities - Collaborate with research engineers on **model quality gates** before production promotion - Build **observability dashboards** for real-time model health across environments - Optimize model serving infrastructure for **latency, throughput, and cost efficiency** ### You’ll Love This Role If You - Enjoy operationalizing cutting-edge AI models at production scale - Believe infrastructure turns research breakthroughs into customer value - Like designing automated, reliable, self-healing systems - Care about latency and accuracy improvements that materially impact customers - Enjoy cross-functional collaboration to make the organization faster - Want to build deployment/testing systems for a platform serving 200,000+ developers ### It’s Important to Us That You Have - **4+ years** experience in MLOps, DevOps, or infrastructure engineering focused on ML systems - Strong **Python** skills and experience building automation/tooling for ML workflows - Deep experience with **CI/CD** and pipelines for software + model delivery - Hands-on **Docker** and **Kubernetes** for containerized workloads - Practical experience deploying/serving ML models in production - Familiarity with **model evaluation, validation, and QA** - Understanding of **monitoring/observability** for ML systems - Strong problem-solving skills and a bias toward **automation** ### It Would Be Great If You Had - Experience with model serving frameworks: **NVIDIA Triton**, **TensorRT**, **ONNX Runtime** - Background in speech/audio/real-time media ML systems - Experience with **Infrastructure as Code** (Terraform, Pulumi) - Hands-on monitoring/observability stacks (Prometheus, Grafana, Datadog, etc.) - GPU-
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.