Production ML Engineer: Scalable Pipelines and Low-Latency

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

Job summary

Evlo AI is seeking an experienced ML Engineer to own end-to-end architecture and deployment of high-throughput machine learning systems. You will design scalable pipelines in Python using PyTorch, deploy and monitor models in cloud environments, and optimize latency for demanding production endpoints.

The role requires 3–6 years in software and ML engineering, strong Python proficiency, and experience with containers and MLOps tools.

Qualifications

• 3–6 years of professional software engineering experience with at least 3 years dedicated to machine learning engineering.
• Strong proficiency in Python and deep experience with PyTorch, TensorFlow, or equivalent ML frameworks.
• Production experience with containerization, orchestration, and MLOps tools like Docker, Kubernetes, and MLflow.
• Solid foundation in software design principles, API development, and distributed computing.
• Bonus: Master’s or PhD in Computer Science, ML, or related field, with open-source ML contributions.

Responsibilities

• Design and implement scalable machine learning pipelines using Python, PyTorch, and distributed data processing frameworks.
• Deploy, monitor, and scale models in production using cloud infrastructure such as AWS or GCP.
• Optimize model inference latency, memory footprint, and throughput for high-traffic endpoints.
• Collaborate with data engineers to establish robust data quality checks across feature stores and training pipelines.
• Conduct rigorous code reviews, establish engineering best practices, and contribute to system architecture discussions.

Skills

Python

PyTorch

TensorFlow

API development

Distributed computing

Education

Master's or PhD (bonus)

Tools

Docker

Kubernetes

MLflow

Job description

Evlo AI is seeking an experienced ML Engineer to own end-to-end architecture and deployment of high-throughput machine learning systems. You will design scalable pipelines in Python using PyTorch, deploy and monitor models in cloud environments, and optimize latency for demanding production endpoints.

The role requires 3–6 years in software and ML engineering, strong Python proficiency, and experience with containers and MLOps tools.