RTML Engineer

Job title: RTML Engineer (Real Time Machine Learning)

Duration: Long-term

Location: Irving, TX

Work Mode: Onsite

Job Description:

What you will be doing:

You will join our critical Real Time ML Service team working on our RTML Model Serving Framework.

This is a fundamental team in our AI Center, and RTML Framework serves all of our real time AI models in the production - enabling our business organizations to maximize the benefits of using AI-driven solutions for our customers.

You’ll need to have:

· Bachelor’s degree or above in Computer Science/Engineering or other related areas.

· Four or more years of work experience in computer software development related jobs.

· At least two years are in AI / ML Engineering areas with reasonably good understanding of Data Science and AIML practices/workflows.

· Strong expertise in RTML model serving arena and/or large scale cloud-based RT framework development.

· Experience with kubernetes. The candidate should be comfortable with kubectl and helm.

· Experience in creating, deploying, and maintaining centralized KubeFlow infrastructure on top of one or multiple kubernetes clusters

· Experience with cloud infrastructures and MLOps in clouds.

· Familiar with CI/CD process and common frameworks such as ArgoCD.

· Experience with programming languages such as Python and Java.

· Experience in large application development in cloud environments - AWS, GCP and On-Prem clusters.

· Experience in K8s architecture and principle of operations, hands-on skills of deploying large applications in production K8s cluster, configuring K8s properly, and troubleshooting when the application has issues.

· Good understanding of of RT system stats collection and performance monitoring methods

· Basic understanding of RT Feature Engineering methodology and practices

· Understand basic data science concepts and common needs from data scientists.