Get AI-powered advice on this job and more exclusive features.
Job Title: Senior Data Scientist
Position Overview
We are looking for a highly skilled and experienced Senior Data Scientist to lead the development and deployment of AI models that extract and process information from unstructured engineering documents—including engineering drawings, CAD/BIM designs, and technical reports.
The ideal candidate has deep expertise in large language models (LLMs) and vision models, with a strong focus on text extraction, summarization, structured data generation, and compliance validation. You will play a key role in advancing AI-driven solutions for the built environment.
Key Responsibilities
- Develop and fine-tune multi-modal LLMs (e.g., LLaMA, GPT) to extract structured data from unstructured documents, including PDFs, Word files, and Excel sheets.
- Implement LLM-based models for interpreting engineering drawings (CAD/BIM), ensuring compliance checks and detecting deviations.
- Build and optimize Retrieval-Augmented Generation (RAG) frameworks for efficient information retrieval and context-aware generation.
- Design and deploy AI pipelines to validate engineering designs against compliance requirements, extract structured data, summarize content, and generate insights.
- Collaborate with software engineers to integrate AI-generated insights into downstream pipelines and reporting systems.
- Ensure high accuracy and reliability by implementing quality control, performance tuning, and error-handling mechanisms.
- Stay at the forefront of AI research, evaluating and implementing new tools for document processing, drawing interpretation, and summarization.
Required Qualifications & Skills
- Bachelor’s or Master’s degree in Machine Learning, Computer Science, or a related field.
- 6+ years of hands-on experience in machine learning, with a strong emphasis on NLP, computer vision, and LLMs.
- Proven expertise in LLMs (GPT, LLaMA, etc.), RAG architectures, vector databases, and document processing tools (e.g., Tesseract, PDFPlumber).
- Strong Python and PyTorch skills, with experience using LangChain/LlamaIndex for AI development.
- Experience deploying AI models in on-premise or secure environments, ensuring compliance with data privacy and security standards.
- In-depth knowledge of text summarization, information extraction, and structured data generation from unstructured sources.
- Strong problem-solving skills and the ability to optimize AI models for real-world applications.
Nice to Have
- Experience with MLOps and AI model lifecycle management.
- Knowledge of AI ethics, regulatory compliance, and responsible AI practices.
- Familiarity with construction, real estate performance metrics, or urban planning applications.
- Contributions to open-source AI/ML or data engineering projects.
Why Join Us?
- Work on cutting-edge AI solutions shaping the future of engineering and urban planning.
- Make a real impact by solving complex, real-world problems in a high-stakes industry.
- Collaborate with top AI experts in a dynamic and supportive environment.
- Gain hands-on experience with the latest advancements in LLMs, RAG, and multi-modal AI.
- Opportunities for career growth and skill development in an evolving AI landscape.
If you're passionate about advancing AI for engineering and urban planning, we’d love to hear from you! Apply now!
Seniority level
Mid-Senior level
Employment type
Full-time
Job function
Engineering and Information Technology
Industries
Civil Engineering