AI Engineers

Automatically extract equipment and system names from plant project contracts (PDFs)
Design NLP pipelines to classify and map technical document names, types, and specifications Integrate OCR and PDF parsing systems to handle multilingual technical documents Work with construction domain experts to continuously refine document classification logic Automate Excel output generation based on AI analysis results
Match extracted data against predefined document templates (Master Document List) Identify and add missing document requirements by analyzing unstructured ITB content
Build and maintain scalable pipelines for document ingestion, analysis, and reporting

3- 5 years of experience in AI, machine learning, or NLP, especially on document intelligence tasks Proficiency in: PDF parsing libraries (e.g., PyMuPDF, pdfminer.six, PDFPlumber) OCR tools (e.g., Tesseract, Google Vision, Amazon Textract) NLP frameworks (e.g., spaCy, NLTK, Hugging Face Transformers)
Bachelor&039;s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or related field
Data processing and automation with Python and Excel (pandas, openpyxl) Experience in named entity recognition (NER), document classification, and information extraction Familiarity with project document types used in construction, plant, or EPC (Engineering, Procurement, Construction) projects is a strong plus

Friendly environment, encourage workers to develop ability
Social insurance and annual leaves according to labor law
Applying and willing to update newest technology.
Tet holiday, daily coffee, snack, facilities

Cập nhật gần nhất lúc: 2025-08-01 02:25:02