Location
London

Hours
Full Time

Salary
Competitive, commensurate with experience

About the Role
Unilabs is one of Europe's leading diagnostics groups, employing 12,500 people across 200+ laboratories in 14 countries, performing over 237 million diagnostic tests annually. Within pathology, Unilabs processes tens of thousands of histopathology cases each year, with flagship digital pathology centres operating at full capacity in Geneva and Lausanne.

As an AI Native Engineer, you will design, build, and maintain advanced LLM-based extraction pipelines to parse unstructured pathology reports and extract critical clinical entities such as diagnoses, tumor grades, pathological staging, and biomarker statuses. You will evaluate and integrate agentic frameworks like LangChain or LlamaIndex, focusing on measurable extraction accuracy.

You will architect multi-modal data pipelines linking pathology LIS data with molecular/genetics systems, ensuring seamless integration of vital markers (KRAS, NRAS, BRAF, MMR/MSI, ctDNA) with histology diagnoses. Your work will include implementing robust REST APIs and HL7 interfaces to feed structured data into downstream systems such as Proscia Concentriq and Aperture, and laying the groundwork for future high-throughput API layers interfacing with consumer wearables and cloud-native hospital systems.

Additionally, you will develop automated data quality monitoring systems to detect anomalies and incomplete records before delivery, implement de-identification protocols aligned with strict health data privacy regulations (Swiss nDSG, EU GDPR Article 9), and build exhaustive audit logging and data lineage tracking to preserve clinical data provenance for pharma and clinical partners.

Experience
- Practical, hands-on experience with LLM APIs, prompt engineering, and building system prompt state machines for structured text extraction.
- Direct experience with agentic frameworks such as LangChain, LlamaIndex, or equivalent for orchestrating complex clinical data workflows.
- Proven track record of shipping non-deterministic models into production, managing context windows, token costs, rate limits, and output evaluation metrics.
- 4–7+ years of core software engineering experience with deep mastery of Python and SQL, capable of debugging asynchronous, multi-step pipelines independently.
- Strong familiarity with designing and consuming production-grade REST APIs in regulated or clinical environments.
- Practical deployment experience on cloud platforms (AWS, Azure, or GCP) using Docker containerization.
- Preferred knowledge of clinical health data standards such as HL7 v2, FHIR, OMOP CDM, and CDISC.
- Exposure to digital pathology data formats (DICOM, SVS, NDPI) or LIS systems is a plus.

About you
You are comfortable working in AI-assisted environments using tools like Cursor or GitHub Copilot to accelerate problem-solving. You focus on delivering high-quality, production-ready solutions rather than manual coding volume. You thrive in a regulated clinical environment and are motivated by building impactful healthcare technology.

Qualifications
Relevant degree or equivalent experience in software engineering, computer science, or related fields. Strong commitment to data privacy, security, and regulatory compliance in healthcare settings.