Applied Scientist, NLP/GenAI(m/w/x)

Anforderungen

• PhD in Computer Science, AI, NLP, or related field, or Master's with equivalent research/industry experience
• 3+ years experience building/deploying document understanding, information extraction, or knowledge graph systems (deep learning, LLMs, NLP)
• Ability to translate complex document understanding problems into innovative AI applications
• Professional experience scaling and leading in applied research
• Strong programming skills (Python) and modern deep learning frameworks experience
• Publications at relevant venues (ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD)
• Deep understanding of document understanding fundamentals (layout analysis, semantic chunking, classification, taxonomies, multi-label, domain schemas)
• Expertise in knowledge extraction and knowledge graph construction (entity recognition, relation extraction, citation parsing, graph representations)
• Expertise in LLM-based information extraction, few-shot/multi-task learning, post-training, knowledge distillation
• Solid understanding of synthetic data generation techniques for NLP (query-answer generation, data augmentation)
• Solid understanding of efficiency optimization (knowledge distillation, model compression, SLM-based solutions)
• Solid understanding of DL/ML approaches for NLP tasks
• Experience designing annotation workflows, creating labeled datasets, and developing evaluation frameworks
• Prior work on legal document understanding, information extraction, knowledge representation (legal citations, domain concepts), or legal AI applications
• Prior work handling complex legal document structures (non-uniform formatting, nested hierarchies, cross-references, embedded elements)
• Experience building systems for analysis, question answering, or retrieval across large document collections
• Experience with knowledge graph frameworks/methodologies for legal or enterprise applications
• Understanding of RAG and agentic workflows for enterprise knowledge
• Publications at relevant venues (ACL, EMNLP, ICLR, NeurIPS, SIGIR, KDD)
• Experience with AzureML or AWS SageMaker

Aufgaben

• Develop and deploy AI solutions for legal document understanding.
• Develop advanced models for semantic chunking lengthy legal documents.
• Build document enrichment systems for classification and rich metadata extraction.
• Create LLM-based pipelines for extracting and linking legal knowledge.
• Develop scalable synthetic data generation systems.
• Support model training with synthetic data.
• Simulate complex legal research queries.
• Generate hallucination-free answers.
• Collaborate with engineering for software delivery and reliability.
• Develop comprehensive data and evaluation strategies.
• Leverage human annotation and synthetic data for evaluation.
• Apply robust training and evaluation methodologies.
• Balance model performance with latency requirements for SLM solutions.
• Apply knowledge distillation to compress models into efficient SLMs.
• Determine appropriate architectures for challenging document understanding.
• Develop semantic chunking strategies for diverse documents.
• Design document classification approaches for legal taxonomies.
• Implement LLM-based knowledge extraction methods.
• Build multi-document reasoning architectures.
• Balance accuracy, efficiency, and scalability for real-world challenges.
• Partner with Engineering and Product to translate legal challenges.
• Engage stakeholders to understand use case requirements.
• Align document understanding capabilities with business needs.
• Maintain scientific and technical expertise in relevant areas.

Berufserfahrung

Ausbildung

Sprachen

Tools & Technologien