Site Reliability Engineer (AI & ML Infrastructure)

Location: USA - Remote

Base salary: $136,000–$240,000 annually, depending on work location, skills, and experience. Equity and bonuses are offered separately.

Company

Deepgram provides real-time voice AI APIs and self-hosted software for speech-to-text, text-to-speech, and production voice agents.

What you will do

• Architect and operate Kubernetes-based computing platforms across AWS and on-premises bare-metal data centers.
• Build reproducible, versioned infrastructure with Terraform and other Infrastructure-as-Code practices.
• Design AI/ML workload scheduling and orchestration, integrating Slurm with Kubernetes for GPU-intensive workloads.
• Manage high-performance GPU servers, hybrid networking, service mesh, and storage solutions including CNI, CSI, and S3.
• Develop monitoring, logging, tracing, operational automation, incident response, and performance-tuning systems.
• Collaborate with AI researchers and ML engineers to build self-service tools and automate the lifecycle of single-tenant managed deployments.

Requirements

• Must be based in the USA.
• 5+ years of experience in Platform Engineering, DevOps, or Site Reliability Engineering.
• Hands-on experience building and managing production infrastructure with Terraform.
• Expert knowledge of Kubernetes architecture and operations in large-scale environments.
• Strong scripting and automation skills with Python, Go, or Bash.
• Experience with CI/CD systems such as GitLab CI, Jenkins, or ArgoCD, and with developer tooling.

Nice to have

• Experience with Slurm and high-performance computing for GPU-intensive AI workloads.
• Experience managing bare-metal infrastructure, including PXE boot, MAAS, provisioning, and lifecycle management.
• Knowledge of FinOps and cloud cost optimization.
• Experience with Kubernetes networking and storage technologies such as Calico, Cilium, Ceph, or Rook.
• Experience in multi-region or hybrid cloud environments.

Culture & Benefits

• AI use and experimentation are core expectations for every team member.
• Work focuses on rapidly evolving AI technologies and continuous learning.
• Infrastructure is treated as a product, with emphasis on developer and researcher experience.
• Equity and performance bonuses are offered in addition to base salary.