ML Data Engineer

This is a fully remote position, open to applicants anywhere in the world.

📋 Description

• Take ownership of monitoring and reporting on CV accuracy metrics, tailored for each customer and identifier type.

• Analyze misclassifications and false negatives, classify root causes, and detect patterns across various customers and yard operations.

• Curate, label, and prioritize datasets for model retraining, collaborating closely with our ML and CV engineering teams.

• Develop and enhance the continuous learning pipeline to ensure new models are deployed weekly with minimal manual intervention.

• Establish functional acceptance criteria for CV accuracy specific to each customer and monitor progress against these benchmarks.

• Interpret accuracy insights into actionable decisions for the engineering team and customer-facing stakeholders.

• As the pipeline evolves, anticipate a shift from merely identifying issues to directly resolving them; this includes constructing labeling/preprocessing tools, executing retraining tasks, and taking responsibility for rectifying the error patterns you uncover, rather than just reporting them.

⛳️ Requirements

• Minimum of 3 years in data quality, ML data engineering, or an applied ML position.

• Proven experience with computer vision or object detection systems deployed in production environments.

• Proficient in Python for data analysis, pipeline automation, and dataset tooling.

• Strong analytical skills, with the ability to delve into extensive volumes of imagery/data to identify patterns, rather than simply executing scripts and reporting figures.

• Familiarity with dataset annotation/labeling tools and workflows (e.g., Roboflow, Labelbox, CVAT, or similar).

• Excellent communication skills in English — you articulate clearly and engage effectively in asynchronous communication.

🏝️ Benefits

• Outpost is an Equal Opportunity Employer and Prohibits Discrimination of Any Kind.