Data Engineer, Document AI & Scientific Data Extraction

Interclypse, Inc.•Gaithersburg, MD
•$105,000 - $115,000•Onsite

About The Position

Interclypse is building a team to support the National Institute of Standards and Technology in making scientific research data machine-readable. The work transforms figures, tables, and instrument output in published reports into standardized, discoverable data for researchers in the semiconductor and advanced manufacturing community. Extraction accuracy is reported monthly and must meet expectations. The Data Engineer will develop document and data extraction pipelines, normalize varied scientific data formats, validate and clean extracted data, and build review interfaces for domain scientists. The tooling will be deployed as microservices within an existing web application and integrated with a downstream discovery portal. The role is on-site in Gaithersburg, Maryland. Interclypse describes a growth-mindset culture with tools, mentorship, and a supportive environment for career development. The team’s code is published publicly, and the company emphasizes positive impact and its motto, “Doing What is Right.”

Requirements

  • Bachelor’s degree in Computer Science, Data Engineering, or a related field.
  • At least 4 years of advanced Python experience, specifically with Pandas and OCR libraries.
  • At least 4 years of experience with OCR pipelines and table extraction logic.
  • At least 4 years of experience in data format normalization and schema validation.
  • At least 4 years of experience integrating microservices into web applications.
  • Able to work on-site in Gaithersburg, Maryland.

Nice To Haves

  • Experience with document layout analysis or document-AI models such as table transformers and layout models.
  • Experience with scientific or laboratory instrument data.
  • Experience with Django, MongoDB, and Docker.
  • Open-source contributions; the team’s code is published publicly.
  • Prior federal clearance or suitability determination.

Responsibilities

  • Build pipelines to detect, crop, and extract figures and charts from scientific documents, capturing captions and identifying axis labels and units through OCR and layout analysis.
  • Develop algorithms to extract embedded tables from PDF and DOCX files while preserving row and column structure and headers.
  • Create parsers that convert non-standard formats, including instrument ASCII dumps, spreadsheets with complex or merged headers, and loose text files, into clean, schema-valid CSV.
  • Implement schema validation and heuristic cleanup for missing values, merged cells, and trailing metadata, flagging ambiguous cases for expert review.
  • Build review interfaces so domain scientists can validate extracted assets and correct OCR errors before ingestion.
  • Deploy tooling as microservices inside an existing web application and integrate it with a downstream discovery portal.
  • Report extraction and parsing accuracy metrics and improve them.

Benefits

  • Employee Impact Program rewarding contributions to the long-term health of the company, customer, and employee.
  • Personal Time Off (PTO) for vacations, holidays, and illnesses.
  • Parental leave.
  • Bereavement leave.
  • Jury duty leave.
  • Retirement plan with 401(k) match up to 8% of salary, subject to the federal maximum.
  • Financial education and planning.
  • Health insurance, including medical, dental, and vision.
  • Health Savings Account (HSA).
  • Medical and dependent care Flexible Spending Accounts (FSA).
  • Employee Assistance Program.
  • Life insurance.
  • Accidental Death and Dismemberment insurance.
  • Short-term and long-term disability coverage.
  • Educational support.
  • $200 per year for company apparel.
  • Company social events, including a holiday party, spring picnic, fall picnic, and happy hours.
  • Access to group rates for voluntary benefits such as accident, hospital indemnity, critical illness, pet insurance, and identity theft protection.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service