MLOps Engineer

Evlo AI; Austin (TX); On-site; USD 120,000 - 180,000; Full time

Job summary

Evlo AI is seeking an experienced MLOps Engineer to own the infrastructure and CI/CD pipelines that scale ML models from prototype to high-throughput, fault-tolerant production environments.

You will collaborate with data scientists and software engineers to ensure automated, secure, and reproducible deployments across cloud infrastructure, with a focus on scalable MLOps practices and robust data governance.

Qualifications

• 3–6 years of experience in MLOps, DevOps, or machine learning engineering with a heavy focus on infrastructure and tooling.
• Strong proficiency in Python, Bash, and infrastructure-as-code tools such as Terraform or CloudFormation.
• Hands-on experience with Kubernetes, Docker, and major cloud platforms (AWS, GCP, or Azure).
• Deep understanding of model serving patterns, containerization, and distributed computing frameworks like Spark or Ray.
• Bonus: Experience managing LLM serving pipelines and vector databases in production.

Responsibilities

• Design, build, and maintain production MLOps infrastructure using Kubernetes, Docker, and Terraform
• Implement automated CI/CD pipelines for machine learning model training, validation, and deployment
• Monitor deployed production models for drift, latency anomalies, and infrastructure degradation using Prometheus and Grafana
• Optimize model serving runtimes and inference costs using tools like Triton Inference Server, ONNX, and vLLM
• Establish robust data governance, lineage tracking, and feature store architectures using tools like Feast or MLflow

Skills

Python

Bash

Terraform

CloudFormation

Kubernetes

Docker

Prometheus

Grafana

Triton Inference Server

ONNX

vLLM

Feast

MLflow

Tools

Kubernetes

Docker

Terraform

CloudFormation

Prometheus

Grafana

Triton Inference Server

ONNX

vLLM

Feast

MLflow

Job description

About The Role

The role owns the infrastructure and CI/CD pipelines that scale machine learning models from prototype to high-throughput, fault-tolerant production environments.

About The Role

The role owns the infrastructure and CI/CD pipelines that scale machine learning models from prototype to high-throughput, fault-tolerant production environments. The team collaborates closely with data scientists and software engineers to ensure automated, secure, and reproducible deployments across cloud infrastructure.

Key Responsibilities

• Design, build, and maintain production MLOps infrastructure using Kubernetes, Docker, and Terraform
• Implement automated CI/CD pipelines for machine learning model training, validation, and deployment
• Monitor deployed production models for drift, latency anomalies, and infrastructure degradation using Prometheus and Grafana
• Optimize model serving runtimes and inference costs using tools like Triton Inference Server, ONNX, and vLLM
• Establish robust data governance, lineage tracking, and feature store architectures using tools like Feast or MLflow

What We Are Looking For

• 3–6 years of experience in MLOps, DevOps, or machine learning engineering with a heavy focus on infrastructure and tooling
• Strong proficiency in Python, Bash, and infrastructure-as-code tools such as Terraform or CloudFormation
• Hands‑on experience with Kubernetes, Docker, and major cloud platforms (AWS, GCP, or Azure)
• Deep understanding of model serving patterns, containerization, and distributed computing frameworks like Spark or Ray
• Bonus: Experience managing LLM serving pipelines and vector databases in production