Principal AI Ops Engineer
New
R
RxSenseHealthcare Technology
Remote (US)Full-TimePrincipal
Salary190,000 - 225,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 6+ years of platform, infrastructure, or DevOps engineering, with at least 2 years building production infrastructure for AI/ML or LLM-powered systems.
- Required Skills
- AWSPythonKubernetesTypeScript.NETCI/CDDevOpsLLM
Requirements
- BS or higher in Computer Science or related technical field.
- 6+ years of experience in platform, infrastructure, or DevOps engineering.
- 2+ years of experience building production infrastructure for AI/ML or LLM-powered systems.
- Deep hands-on experience designing and operating CI/CD pipelines.
- Strong AWS background including IAM, networking, and container orchestration.
- Proven track record of building adopted developer platforms or internal tools.
- Production experience with LLM applications including prompt management and model routing.
- Hands-on coding fluency in Python or TypeScript.
- Comfort working in a polyglot environment (Python, .NET, TypeScript).
- Strong written communication skills with a focus on documentation and runbooks.
Responsibilities
- Build and maintain end-to-end CI/CD deployment pipelines for AI applications.
- Operate runtime and lifecycle infrastructure for production agents, including monitoring and versioning.
- Manage and secure model provider API access, quotas, and cost attribution.
- Implement evaluation frameworks within CI/CD pipelines to gate production deployments.
- Deploy and manage self-hosted inference infrastructure, including GPU autoscaling and cost optimization.
- Design shared developer harnesses for prompt management, routing, and tracing.
- Partner with finance and engineering teams on AI cost observability and infrastructure reliability.
View Full Description & ApplyYou'll be redirected to the employer's site
