D
$160,000 – $220,000
Listed on Deepgram’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
This role bridges research and production at an AI voice platform, building the infrastructure that takes experimental models through CI/CD pipelines to serving millions of API requests. You'll own deployment automation, monitoring, and testing systems for machine learning models at scale.
Our summary, not Deepgram’s wording. The full posting is on their site.
Skills this role names
Log in to see which of these are already on your profile.
What they ask for
Required
- 4+ years of MLOps, DevOps, or infrastructure engineering experience focused on ML systems
- Proficiency in Python for ML automation and tooling
- Deep experience with CI/CD systems for software and model delivery
- Hands-on Docker and Kubernetes for containerized workloads
- Production ML model deployment and serving experience
- Understanding of model evaluation and quality assurance processes
- Knowledge of monitoring and observability for ML systems
- Strong problem-solving with bias toward automation
Nice to have
- Experience with model serving frameworks like NVIDIA Triton, TensorRT, or ONNX Runtime
- Background in speech, audio, or real-time media ML systems
- Infrastructure as Code tools such as Terraform or Pulumi
- Hands-on monitoring stacks like Prometheus, Grafana, or Datadog
- GPU-accelerated inference optimization and profiling
- Feature stores, data versioning, or ML metadata management
- Canary deployment and progressive delivery strategies for models