🛠 Tech Stack

💼 About This Role

You'll build knowledge extraction engines for Materials Science, tackling complex table reconstruction, experimental workflow synthesis, and multimodal chart analysis from patents and papers. Your work will transform unstructured scientific literature into structured R&D databases. You'll leverage NER, RAG, and post-training to achieve high-value data extraction.

🎯 What You'll Do

• Develop end-to-end data extraction pipelines integrating OCR and layout analysis.
• Resolve cross-modal data alignment between text and scientific visuals.
• Design and implement robust RAG systems with hybrid search and ranking optimization.
• Enhance LLMs' reasoning and understanding via post-training techniques.

📋 Requirements

• Bachelor's degree in Computer Science, AI, or related field.
• 3+ years of hands-on experience in NLP/LLM/RAG with production deployments.
• Proficient in Python and algorithmic implementation.
• Ability to understand product requirements and solve data/RAG challenges cross-functionally.

✨ Nice to Have

• Deep experience in high-quality data processing and production-grade RAG systems.
• Proven ability to enhance extraction accuracy through post-training techniques.
• Familiarity with Physics, Chemistry, or Biology.