3 months ago
London, United KingdomSenior
Responsibilities
- Design and build generative AI applications for complex financial and legal workflows.
- Lead the end-to-end model development lifecycle, including experimentation, training, testing, evaluation, deployment, and monitoring.
- Build high-precision document extraction systems using schema-driven extraction, citation grounding, validation, and confidence scoring.
- Develop review, verification, reconciliation, retrieval, context-engineering, and data-quality workflows for long documents.
- Create labelled datasets, annotation frameworks, synthetic data, and evaluation sets for document extraction.
- Build and operate production extraction pipelines, evaluation systems, model-serving infrastructure, and monitoring.
- Collaborate cross-functionally, translate business problems into scoped initiatives, mentor teammates, and promote AI adoption across the organization.
Requirements
- Deep experience with complex legal and financial documents, including bond offering memoranda, credit agreements, indentures, court filings, and transaction documentation.
- Expertise extracting structured financial and legal information such as terms, covenants, definitions, parties, dates, thresholds, baskets, ratios, and transaction mechanics.
- Strong understanding of document structure, section hierarchies, cross-references, defined terms, tables, exhibits, and legal-document patterns.
- Experience applying LLMs to high-precision structured extraction tasks, including grounding, validation, and confidence scoring.
- Experience designing data-quality, review, verification, reconciliation, training-data, annotation, synthetic-data, and evaluation systems.
- Strong understanding of chunking, document segmentation, retrieval, and context construction for long-document reasoning.
- Familiarity with leveraged finance, debt capital markets, credit agreements, covenant packages, bond documentation, restructuring, and related legal concepts.
- Ability to build and operate production ML pipelines, evaluation systems, model-serving infrastructure, and monitoring.
- Strong proficiency in Python for production-ready delivery.
- Experience across the full model lifecycle, including experimentation, training, testing, monitoring, and deployment.
- Strong product focus and desire to understand the end-to-end impact of solutions on users.
- Good knowledge of AWS AI infrastructure.
Benefits
- Competitive salary, equity, pension contributions with employer matching, private medical insurance, paid sick leave with income protection, and group life assurance.
- Season ticket loan and Cycle to Work schemes.
- 25 holiday days per year plus local public holidays, with the option to exchange holidays for alternative days.
- Hybrid working model with flexibility over when and where to work.
- Ability to work abroad for up to three months per year.
- One month of paid sabbatical after five years of service.
- Enhanced parental leave and flexible working arrangements.
- Professional learning and development budget and an £800 annual AI experimentation budget.
- Quarterly team socials and summer and winter company events.
Categories
