Data Science Intern, Asset Intelligence

This is a fully remote position, open to applicants in New York.

📋 Description

• Track asset records from initial customer intake through processes of normalization, classification, and enrichment.

• Replicate the production pipeline using sample data and verify that the results align.

• Record service decisions, evidence utilized, and delicate judgments made.

• Develop and sustain a benchmark reference set of accurately classified instruments.

• Evaluate match rates and classification accuracy by equipment category.

• Reassess scores following any changes to illustrate improvement.

• Group near-duplicate records and align them with their alias collections.

• Enhance classifier input text by differentiating technical capability language from application and use-case terminology.

• Examine attribute coverage across the record base on a field-by-field basis.

• Manage code and queries within the team repository.

• Document method notes alongside code for seamless handoff.

• Conduct ad hoc data extractions and analyses for the team.

⛳️ Requirements

• Currently pursuing a bachelor's degree in data science, statistics, computer science, or a related discipline.

• Proficient in Python and SQL.

• Available for approximately ten hours per week during the academic term.

• Academic or project experience in data cleaning, record matching, deduplication, or classification.

• Familiarity with pandas and Jupyter, or their equivalents in R.

• Some experience with AI-assisted text processing, with a tendency to verify results rather than accept them blindly.

• Ability to work remotely following written instructions with minimal supervision.

• Strong written communication skills.

• Interest in scientific instrumentation or laboratory operations; prior domain knowledge is not necessary.

🏝️ Benefits

• Competitive hourly pay ranging from $25 to $40 per hour.

• Part-time schedule of around ten hours per week during the academic term.

• Flexible remote work arrangement.