ML Data Engineer

About the role

This role focuses on ensuring the accuracy of our computer vision systems that power freight logistics. You will be responsible for measuring performance, understanding errors, and creating the labeled data that improves our machine learning models. As the system matures, you will also contribute directly to product fixes.

Key facts

What you'll do

• Track and report on computer vision accuracy for customers and different identification types.
• Analyze misclassifications and false negatives, categorizing their causes and identifying trends.
• Prepare, label, and prioritize data for model updates, collaborating with ML and computer vision engineers.
• Enhance the continuous learning pipeline to enable frequent model deployments with minimal manual effort.
• Establish and monitor functional acceptance criteria for computer vision accuracy per customer.
• Translate accuracy insights into actionable recommendations for engineering and customer-facing teams.
• As the pipeline evolves, take on direct issue resolution, including building tooling and owning fixes for identified error patterns.

Requirements

• A minimum of 3 years of experience in data quality, ML data engineering, or applied ML.
• Proven experience with production computer vision or object detection systems.
• Proficiency in Python for data analysis, automation, and dataset tooling.
• Strong analytical skills to uncover patterns in large image and data sets.
• Experience with dataset annotation and labeling tools such as Roboflow, Labelbox, or CVAT.
• Excellent written and asynchronous communication skills in English.

Nice to have

• Experience with continuous learning or active learning pipelines for production ML.
• Familiarity with OCR systems and recognizing identifiers like license plates or container numbers.
• Experience working with customer success or support teams on quality metrics.
• Background in QA or test engineering for ML systems.
• Specific experience with Roboflow.

Skills & tools

• Python
• Roboflow
• VLM/OCR pipelines
• GCP (GCS)
• PostgreSQL
• Snowflake
• Node.js/TypeScript

Practical notes

• Visa sponsorship is not available for this role.
• No travel is expected.
• Outpost is an Equal Opportunity Employer.