ENGINEERING
DevOps Engineer, AI Infrastructure
Run the platforms our AI delivery teams and clients build on. You will own CI/CD for model-backed services, GPU capacity, and the paved road that lets an engagement go from notebook to governed production deployment.
- Dallas
- Engineering
- Full-time
What you’ll do
- Design and operate CI/CD pipelines that treat prompts, model versions and eval suites as deployable artefacts
- Manage GPU and inference capacity across client environments, balancing cost, latency and quota limits
- Automate provisioning of secure, client-isolated AI environments with IaC
- Build monitoring for model endpoints: latency, token spend, drift and failure fallbacks
- Advise client platform teams on running LLM workloads without surprises
What we’re looking for
- 3+ years in DevOps or platform engineering, including infrastructure for ML or LLM workloads
- Strong Kubernetes and Docker experience, ideally with GPU scheduling and autoscaling inference services
- Infrastructure-as-code fluency (Terraform, Pulumi) across AWS, Azure or GCP AI stacks (Bedrock, Azure OpenAI, Vertex AI)
- Experience wiring CI/CD for systems that include prompts, models and evals — not just code
- Strong scripting skills (Python, Bash) and familiarity with observability tooling
What we offer
- Competitive salary
- Comprehensive benefits package
- Flexible work arrangements
- Certification and continuous learning budget
- Dedicated homelab and cloud sandbox allowance