ML Scientist: Document Intelligence & NLP Expert

Brooksource; Lansing (MI); On-site; USD 90,000 - 130,000; Full time

Job summary

Brooksource in Lansing, MI is seeking a hands-on machine learning engineer to develop and evaluate models using Python, and to build solutions for document classification, segmentation, and information extraction.

You will clean, parse, explore, and model real-world data; perform model evaluation and error analysis; document methodologies and results; and clearly communicate findings to both technical and non-technical stakeholders while moving models toward repeatable production workflows.

Qualifications

• 2–5 years of hands-on ML experience with Python.
• Experience with data preparation, modeling, evaluation, and error analysis.
• Strong analytical and problem-solving skills.
• Ability to assess model performance and communicate limitations.
• Strong written and verbal communication skills.
• Ability to work independently and collaboratively in ambiguous environments.

Responsibilities

• Develop and evaluate ML models using Python.
• Clean, parse, explore, and model messy real-world data.
• Build solutions for document classification, segmentation, and information extraction.
• Perform model evaluation and error analysis to identify strengths and weaknesses.
• Document methodologies, assumptions, experiments, and results.
• Clearly communicate technical findings to both technical and non-technical stakeholders.
• Work independently on ambiguous modeling problems and collaborate with technical partners.
• Help move successful models toward repeatable production workflows.

Skills

Machine Learning

Python

Data analysis

Communication skills

Job description

Brooksource in Lansing, MI is seeking a hands-on machine learning engineer to develop and evaluate models using Python, and to build solutions for document classification, segmentation, and information extraction.

You will clean, parse, explore, and model real-world data; perform model evaluation and error analysis; document methodologies and results; and clearly communicate findings to both technical and non-technical stakeholders while moving models toward repeatable production workflows.