ML Systems Engineer - Scalable Data Pipelines & Training

HTU; Bellevue (WA); On-site; USD 92,000 - 138,000; Full time

Benefits offered by this job

Health insurance

Life insurance

Disability insurance

Commute subsidy

Stock options

Retirement plan

Vacation days

Parental leave

Office snacks

Wellbeing programs

ERGs

Assistance program

Training program

Volunteer program

Job summary

HTU in Bellevue, WA is seeking an ML Infrastructure Engineer to build and maintain data pipelines that generate training datasets for machine learning models. You will support distributed training workflows with PyTorch and Ray and work with orchestration tools like Airflow and Flyte for multi-stage ML pipelines.

You will partner with ML engineers to improve reproducibility, reliability, and performance across data processing and training systems while helping the offline ML platform scale as

Qualifications

• BS in CS, ML, Systems, or related field.
• Experience with Python and data-intensive workloads.
• Experience with ML frameworks and distributed systems.
• Experience with data pipelines or large datasets.
• Strong problem-solving and translating ideas into systems.
• Interest in scalable ML infrastructure.

Responsibilities

• Build and maintain data pipelines for training datasets.
• Contribute to infrastructure for distributed training (PyTorch, Ray).
• Work with workflow tools (Airflow, Flyte) for multi-stage pipelines.
• Improve reproducibility via dataset validation and testing.
• Collaborate with ML engineers on experiments and model iteration.
• Optimize performance and efficiency across data processing and training.
• Contribute to offline ML platform architecture as it scales.

Skills

Python

ML systems

Distributed systems

Data processing

Research to production

Education

Bachelor's degree in CS/ML

Tools

PyTorch

TensorFlow

Ray

Spark

Airflow

Flyte

Job description

HTU in Bellevue, WA is seeking an ML Infrastructure Engineer to build and maintain data pipelines that generate training datasets for machine learning models. You will support distributed training workflows with PyTorch and Ray and work with orchestration tools like Airflow and Flyte for multi-stage ML pipelines.

You will partner with ML engineers to improve reproducibility, reliability, and performance across data processing and training systems while helping the offline ML platform scale as