Machine Learning Data Engineer (Contract)

Role overview A vertically integrated logistics and technology company is hiring a contract Machine Learning Data Engineer to own the accuracy of its production computer vision system, which automates truck gates at terminals across the United States. As new customers onboard, the CV pipeline encounters a wider variety of camera layouts and identifier types than ever, and your job is to measure accuracy, diagnose misclassifications, and turn those findings into the labeled data and tooling that retrain better models. Initially focused on measurement and curation, the role is expected to evolve into direct ownership of fixes inside the product itself.

Responsibilities - Track and report CV accuracy metrics per customer and per identifier type - Investigate misclassifications and false negatives, categorize root causes, and surface patterns across customers and yards - Curate, label, and prioritize datasets for model retraining in close partnership with ML and CV engineers - Build and improve the continuous learning pipeline so new models ship weekly with minimal manual engineering effort - Define functional acceptance criteria for CV accuracy per customer and track progress against them - Translate accuracy findings into actionable decisions for engineering and customer-facing stakeholders - As the pipeline matures, move from flagging issues to fixing them directly: build labeling/preprocessing tooling, run retraining jobs, and own fixes for the error patterns you surface

Requirements - 3+ years in data quality, ML data engineering, or applied ML roles - Hands-on experience with computer vision or object detection systems in production - Comfortable writing Python for data analysis, pipeline automation, and dataset tooling - Strong analytical rigor, with the ability to dig into large volumes of imagery and find patterns rather than just reporting a number - Experience with dataset annotation and labeling tools such as Roboflow, Labelbox, or CVAT - Strong English communication skills with clear writing and effective async collaboration

Nice to have - Experience with continuous learning or active learning pipelines for production ML systems - Familiarity with OCR systems and identifier recognition such as license plates and container numbers - Background partnering with customer success or support teams on quality metrics - Experience in QA or test engineering for ML systems - Direct experience with Roboflow

Benefits and work setup - Full-time remote contract role, Latin America preferred - Embedded in core engineering sprints, standups, and Slack channels; employment is managed through an agency partner - Stack includes Python, Roboflow, VLM/OCR pipelines, GCP (GCS), PostgreSQL, Snowflake, and Node.js/TypeScript