Senior NLP Engineer — Document-Level Info Extraction

Patsnap; Singapore; On-site; SGD 150,000 - 190,000; Full time

Job summary

Patsnap is seeking a Senior Machine Learning Engineer to own an information-extraction pipeline for patents and scientific literature. You will prototype, ship improvements, and raise extraction precision to production-grade level.

You will work hands-on on long documents, integrating NER, rules, and LLMs, with end-to-end ownership from modeling to deployment in an in-office Singapore role.

Qualifications

• Bachelor's or Master's in CS or related field.
• 4+ years of hands-on NLP/ML engineering in production.
• Proven experience with long-document information extraction and normalization.
• Solid engineering fundamentals for working at scale.
• Strong in NER and entity methods across rule-based, statistical, and LLM-based approaches.
• Strong coding skills.

Responsibilities

• Analyse and understand large structured and unstructured data using NLP tasks (data processing, NER, relationship extraction, NOR).
• Own and improve the information-extraction pipeline from model to production.
• Address document-level extraction challenges across long documents and cross-section relationships.
• Drive algorithm optimization and fine-tune models to meet business needs.
• Build hybrid systems combining NER, rules, and LLMs where each excels.
• Define evaluation, annotation strategy, and quality metrics with domain experts.
• Process and extract from large-scale corpora reliably and efficiently.

Skills

NLP/ML engineering

Document-level extraction

NER

LLMs & hybrid systems

Model optimization

Production readiness

Education

Master's or Bachelor's degree in Computer Science or related field

Job description

Patsnap is seeking a Senior Machine Learning Engineer to own an information-extraction pipeline for patents and scientific literature. You will prototype, ship improvements, and raise extraction precision to production-grade level.

You will work hands-on on long documents, integrating NER, rules, and LLMs, with end-to-end ownership from modeling to deployment in an in-office Singapore role.