- 经验
- 4+ yrs
- 薪水
- —
- 职位空缺
- 1
- 发布
- 1 小时前
- Work mode
- 在办公室
- 学历
- B.Tech
- Eligibility
- Candidates with a bachelor’s or master’s degree in Computer Science or a related field, and at least 4 years of production NLP/ML engineering experience, are suitable for this role.
- Resume
- Required to apply
Where you'll work
职位描述
About the Role
We are looking for a senior NLP-focused engineer to take full ownership of the accuracy and quality of an information-extraction pipeline. The work centers on pulling material properties and quantitative measurements from long, complex sources such as patents and scientific papers, where useful signals are spread across multiple sections and relationships may extend over paragraphs. This is a senior, hands-on position that requires end-to-end ownership: you will scope ideas, build prototypes, ship improvements, define quality measurement approaches, and help raise extraction precision to production standards.
Responsibilities
- Analyze large structured and unstructured datasets using NLP techniques such as data processing, named entity recognition, relation extraction, and related methods.
- Take ownership of the information-extraction pipeline and continuously improve it from model development through production deployment.
- Address document-level extraction challenges by designing solutions for long documents where entities, attributes, and relationships appear across different sections.
- Independently lead algorithm optimization and build or refine models to satisfy business needs.
- Create hybrid solutions that combine NER, rule-based approaches, and LLMs, choosing the right method for each problem.
- Work with domain experts to define evaluation approaches, annotation processes, and quality metrics.
- Reliably process and extract information from very large text corpora with efficiency and stability.
Requirements
- Master’s degree or bachelor’s degree in Computer Science, or a closely related discipline.
- At least 4 years of practical NLP/ML engineering experience in production, with ownership of model or pipeline quality.
- Demonstrated experience in long-document or document-level information extraction and normalization.
- Strong engineering foundations and the ability to work effectively at scale.
- Deep understanding of NER and entity methodology, including rule-based, statistical, and LLM-driven approaches.
- Strong coding ability and familiarity with modern rapid-development practices.
Additional Information
The role is based in Singapore and is a full-time onsite position.