AI Engineers

About Pangaea Data

Pangaea Data (Pangaea) is a provider of a clinically validated AI platform that proactively uncovers care gaps, which cannot be pre-empted or prompted for because they are unknown, thereby delivering reliable, actionable insights that enable earlier intervention, improve quality and patient safety, and make advanced clinical decision support accessible across both high and low resource settings. Pangaea’s founders Dr Vibhor Gupta and Prof Yike Guo (Director Data Science Institute at Imperial College London;

Provost, Hong Kong University of Science and Technology) have worked in medicine and computing for over 20 years and have raised over $300 million through their academic research, including a $110 million grant focused on development work on large language models in medicine. Their advisors include industry veterans from healthcare and the life sciences, including Lord David Prior (former chairman, NHS England) and Mr.

Andy Palmer (former CIO, Novartis).

Pangaea is looking for a skilled AI Engineer to build and productise LLM and agent capabilities in Pangaea’s AI Platform. This is an applied product engineering role rather than primarily a model-training or research position.

You will own capabilities from problem definition through implementation, evaluation, release and monitoring. Typical work includes turning patient notes, FHIR data and clinical guidelines into evidence-grounded structured outputs; building retrieval, reasoning, and tool-using agents; and combining probabilistic models with deterministic clinical logic. You will work closely with clinicians, who remain the authority on clinical interpretation and approval.

• Collaborate with clinicians and product stakeholders to translate clinical problems into explicit data contracts, system behaviour and success measures.
• Design and ship LLM and agent workflows for clinical evidence extraction, retrieval, reasoning, patient identification, guideline-driven review and conversational experiences.
• Build robust LLM integrations using structured outputs, schema validation, tool calling, bounded context and explicit workflow state.
• Develop retrieval and data pipelines across structured clinical data and free text, preserving provenance and links to supporting evidence.
• Create evaluation datasets and regression checks for prompt, model and provider changes, combining automated assessment with clinician review where appropriate.
• Instrument traces, failures, latency, token use and cost, and implement suitable timeout, retry, rate-limit, concurrency and caching behaviour.
• Productise capabilities as maintainable Python services and APIs, delivering small improvements regularly and monitoring their impact after release.
• Integrate AI capabilities with data, backend and frontend systems and contribute to architecture, code review and documentation.
• Gather early feedback from clinicians and internal users and use production telemetry to improve quality and usability.
• Communicate technical trade-offs, limitations, roadmap decisions and product changes clearly before launch.

While expertise across all areas is not required, ideal candidates will possess a solid foundation in production LLMs, complemented by deep specialization in either agent and backend architectures or clinical data analytics and model evaluation.

• Demonstrated experience shipping LLM-enabled software used by real users or operational teams.
• Strong Python and software engineering skills, including typed data models, APIs, automated testing and maintainable system design.
• Hands-on experience with hosted LLM APIs, structured outputs, tool use, retrieval-augmented generation, context management and model…