Description

You will design and build end-to-end text extraction pipelines for policy, regulatory, fintech, and healthcare documents.

This role is on-site.

Responsibilities

• Design and build end-to-end text extraction pipelines for complex document types.
• Fine-tune BERT and RoBERTa models for NER, text classification, and relation extraction tasks.
• Leverage LLM APIs using prompt engineering, tool/function calling, and structured output extraction.
• Build scalable Python pipelines to process high-volume PDF, DOCX, and HTML files.
• Evaluate model performance and implement feedback loops to improve extraction quality.

Required Skills

• 5+ years of hands-on NLP engineering in production pipelines.
• Python programming.
• NLP libraries including spaCy and NLTK.
• HuggingFace Transformers and Deep Learning frameworks.
• LLM API Integration.
• Data Pipeline development.
• JSON Schema definition.
• Pydantic for structured output validation.
• Any Graduate degree.

Preferred Skills

• Experience with legal, regulatory, or policy documents.
• Familiarity with knowledge graphs or graph databases like Neo4j or RDF.

Key Skills

Education

Any Graduate