> Markdown version of [/jobs/ext/2786295-ai-engineers](https://www.wearedevelopers.com/jobs/ext/2786295-ai-engineers). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Engineers - **Company:** Pangaea Data Limited - **Location:** London, UK - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Audit Trail, Automation of Tests, Microsoft Azure, Clinical Data Repository, Code Review, Databases, Elasticsearch, Python (Programming Language), Machine Learning, MongoDB, Open Source Technology, Software Architecture, Regression Testing, Search Technologies, Software Engineering, Privacy Controls, Data Processing, Fast Healthcare Interoperability Resources, Retrieval-Augmented Generation, Large Language Models, Multi-Agent Systems, Model Validation, Backend, Fastapi, Information Technology, Health Level Seven International, Front End Software Development, Data Pipelines - **Published:** September 8, 2026 - **Apply:** https://www.collegerecruiter.com/job/2840624018-ai-engineers ## About the Role 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. Technical Skills * 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 limitations. * Experience evaluating non-deterministic systems using representative datasets, explicit metrics, failure analysis and regression testing. * Experience with databases, search or data-processing systems and diagnosing behaviour across service boundaries. * A rigorous approach to evidence, provenance, ambiguity and safe failure in a high-stakes domain. * A degree in computer science, engineering, data science or a related subject, or equivalent practical experience., * A strong intuition for what makes products a joy to use * Empathy for how different users will need different things out of a product at different stages, and how to effectively serve these different needs in one product * Strong communication and mediation skills * Strong people skills and the ability to engage all levels of the organization (especially the front line). * Ability to work collaboratively in a team environment. * Ability to communicate complex ideas effectively, both verbally and in writing * A strong software engineering background with machine learning expertise to understand how the user facing product will tie into backend and architectural decisions, * Experience with FHIR R4, HL7, LOINC, SNOMED CT or longitudinal clinical data. * Experience in healthcare, life sciences or another regulated or safety-sensitive domain. * Familiarity with FastAPI, Pydantic, MongoDB, Elasticsearch, hybrid or vector search, LangGraph or similar agent frameworks. * Experience with Azure or AWS, containers, on-premise deployments, multi-tenant systems, privacy controls or audit logging. * Experience with embeddings, fine-tuning, open-source models or applied research when these are the right tools for a product problem. ## Description 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. ## Related Videos - [Developing the Backend with Stefan Lingler, CTO at Shpock](https://www.wearedevelopers.com/videos/100360-developing-the-backend-with-stefan-lingler-cto-at-shpock) - [40 Minutes to Build a Serverless COVID-19 REST and GraphQL APIs](https://www.wearedevelopers.com/videos/208-40-minutes-to-build-a-serverless-covid-19-rest-and-graphql-apis) - [Intro to FastAPI](https://www.wearedevelopers.com/videos/462-intro-to-fastapi) - [How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge](https://www.wearedevelopers.com/videos/1328-how-to-avoid-llm-pitfalls-mete-atamel-and-guillaume-laforge) - [NoSQL Data Modeling for Front-end Developers](https://www.wearedevelopers.com/videos/297-nosql-data-modeling-for-front-end-developers) - [Nest.js - TypeScript in the backend can also be clean](https://www.wearedevelopers.com/videos/1033-nest-js-typescript-in-the-backend-can-also-be-clean) ## Related Articles - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models) - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [From Prototype to Production: Build AI Agents with This Free 4-Course Learning Path](https://www.wearedevelopers.com/magazine/655-from-prototype-to-production-build-ai-agents-with-this-free-4-course-learning-path) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift)