Lead Applied Scientist

kadence; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

kadence is seeking a Lead Applied Scientist to advance search-led AI solutions for legal and professional services domains. You will design and deploy end-to-end document understanding systems, build semantic chunking models, and develop knowledge graph pipelines that link heterogeneous legal knowledge across products.

The role demands a PhD or equivalent research experience, leadership skills, and strong deep learning expertise with PyTorch/Transformers.

Qualifications

• Experience building document understanding and information extraction systems.
• Ability to translate complex problems into AI applications balancing accuracy and efficiency.
• Proven leadership, mentoring, and influence in an applied research setting.
• Publications at NLP venues (ACL, EMNLP, NeurIPS, etc.) are preferred.

Responsibilities

• Lead end-to-end AI solutions for complex document understanding tasks in the legal domain.
• Direct execution of large-scale projects: semantic chunking, document enrichment, and knowledge graphs.
• Serve as technical lead with accountability for research deliverables and production readiness.
• Partner with engineering to ensure scalable, reliable software delivery across product lines.

Skills

Hands-on document understanding

Technical leadership

Python

PyTorch / Transformers

Knowledge graphs

Education

PhD in Computer Science / AI / NLP

Master's degree with research/industry experience

Job description

Lead Applied Scientist, Search - NLP/GenAI

This position is based in either Zug, Switzerland or London, UK.

Want to use your experience of building search-led AI solutions to enhance our leading products in the tax, legal and professional services industries?

Document understanding is a foundational intelligence layer that powers every major capability across our legal AI platform—from search and information extraction to agentic reasoning in products. You'll build state-of-the-art semantic chunking, document enrichment, and knowledge graph construction systems that serve as the cognitive foundation multiple product teams depend on, working across authoritative legal, tax, and accounting content and extraordinarily diverse customer data.

This is a rare opportunity to solve publishing-quality research problems with immediate production impact—your innovations will directly shape how millions of legal professionals research, analyze, and reason over complex legal documents while advancing the capabilities that enable the next generation of intelligent legal AI agents.

About the Role

As a Lead Applied Scientist, you will:

• Lead the design, build, test, and deployment of end-to-end AI solutions for complex document understanding tasks in the legal domain
• Direct the execution of large-scale projects including: advanced semantic chunking models for lengthy, non-uniformly structured legal documents with adjustable granularity; document enrichment systems with legal and customer-defined taxonomies; LLM-based knowledge graph construction pipelines that extract and link heterogeneous legal knowledge; and scalable synthetic data generation systems
• Serve as the technical lead and primary point of reference, ensuring full accountability for all research deliverables
• Partner with engineering to guarantee well-managed software delivery and reliability at scale across multiple product lines

Evaluate, Optimize & Advance Capabilities

• Design comprehensive evaluation strategies for both component-level and end-to-end quality, leveraging expert annotation and synthetic data
• Apply robust training methodologies that balance performance with latency requirements
• Lead knowledge distillation initiatives to compress large models into production-ready SLMs
• Maintain scientific and technical expertise through product deliverables, published research, and intellectual property contributions
• Inform Labs shared capabilities and research themes through novel approaches to challenging business problems

Drive Strategic Technical Direction

• Independently determine appropriate architectures for complex document understanding challenges, balancing accuracy, efficiency, and scalability
• Make critical technical decisions on semantic chunking strategies, document classification approaches, LLM-based knowledge extraction methods, and multi-document reasoning architectures
• Provide input to business stakeholders, mid-to-senior level leadership, and Labs leadership on long-term AI strategy
• Develop in-depth knowledge of TR customers and data infrastructure across multiple products to shape technical roadmaps
• Partner closely with Engineering and Product teams to translate complex legal document understanding challenges into scalable, production-ready solutions
• Engage stakeholders across multiple product lines to deeply understand use case requirements, shaping objectives that align document understanding capabilities with diverse business needs including next-generation search and deep legal research
• Mentor and coach team members with varied ML/NLP abilities, building technical capability across the organization

About You

You're a fit for the role of Lead Applied Scientist if you have:

• PhD in Computer Science, AI, NLP, or a related field, or a Master's degree with equivalent research/industry experience
• Demonstrable hands-on experience building and deploying document understanding systems, information extraction pipelines, or knowledge graph construction using deep learning, LLMs, and NLP methods
• Proven ability to translate complex document understanding problems into innovative AI applications that balance accuracy and efficiency
• Demonstrated ability to provide technical leadership, mentor team members, and influence without formal authority in an applied research setting
• Strong programming skills (e.g., Python) and experience with modern deep learning frameworks (e.g., PyTorch, Hugging Face Transformers, DeepSpeed)
• Publications at relevant venues such as ACL, EMNLP, ICLR, NeurIPS, SIGIR, or KDD

Technical Qualifications

• Deep understanding of document understanding fundamentals: document layout analysis, semantic chunking approaches beyond fixed-size or paragraph-based methods, document classification handling hierarchical taxonomies, imbalanced multi-label classification, and adapting to domain-specific schemas
• Expertise in knowledge extraction and knowledge graph construction: entity recognition and linking, relation extraction, citation parsing, and building graph representations from unstructured text
• Expertise in LLM-based information extraction, few-shot and multi-task learning, post-training, and knowledge distillation
• Solid understanding of synthetic data generation techniques for NLP, including query-answer generation with verification and scalable data augmentation for training specialized models
• Solid understanding of efficiency optimization including knowledge distillation, model compression, and designing SLM-based solutions that balance performance with computational constraints
• Solid understanding of DL/ML approaches used for NLP tasks
• Experience designing annotation workflows, creating high-quality labeled datasets with clear guidelines, and developing evaluation frameworks for document understanding tasks