Summary
What you’ll impact
The Senior Machine Learning Ops Engineer designs, builds, and operates infrastructure to deploy and scale AI models across cloud and on‑premise environments. They use Kubernetes, Docker, CI/CD pipelines, an inference server, TensorRT, and multi‑cloud platforms (major cloud providers) for reliable inference services. Responsibilities include automating model lifecycle workflows, optimizing GPU cluster performance, and implementing monitoring and observability for inference pipelines. They partner with senior leadership to translate research into production‑ready systems and support early on‑premise customer deployments.
Responsibilities
What you'll do
- Design, build, and continuously improve CI/CD pipelines that move AI models reliably from development through production, including testing, validation, and deployment automation
- Own inference pipeline reliability and performance across GCP, AWS, Azure, CoreWeave, and on-premise environments, proactively identifying and implementing improvements
- Research and evaluate GPU scaling approaches across hardware architectures to inform infrastructure decisions and extend platform capabilities
- Implement and manage Nvidia Triton Inference Server and leverage Nvidia Fleet Command to streamline model inference workloads
- Manage GPU clusters and deploy models using Kubernetes and Docker to ensure scalable, efficient across all deployment environments
- Automate model retraining and redeployment processes in response to data updates and performance changes
- Monitor system health, performance, and reliability using AI observability tools, with a focus on continuous improvement rather than maintenance alone
- Partner closely with the CTO on infrastructure research initiatives, translating emerging hardware and deployment capabilities into production-ready systems
- Support early on-premise customer installations and contribute to knowledge transfer as Solutions Engineering takes ownership of that function
Requirements
What you’ll bring
- 5+ years of hands-on experience in production
- ML infrastructure engineering, with a track record of deploying and operating AI models at scale
- Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience
- Deep proficiency with Kubernetes and Docker for deploying and managing all workloads across diverse environments
- Hands-on experience with CI/CD pipelines designed for AI and ML model lifecycle management
- Strong working knowledge of Nvidia Triton Inference Server and TensorRT
- Experience designing and managing infrastructure across multiple cloud platforms, including at least two of: GCP, AWS, Azure, CoreWeave
- Solid understanding of GPU cluster management and the performance tradeoffs across hardware configurations
- Experience with on-premise AI deployment and the infrastructure complexity it introduces
- Strong grasp of MLOps principles and AI model lifecycle management from experimentation through production
- Ability to work autonomously, make infrastructure decisions with limited oversight, and communicate technical tradeoffs clearly to senior leadership