(Barcelona based - remote optional)

ML ENGINEER | Healthcare Data Platform · AI & Analytics

(Please send your CV and application - detailed answers to screening questions to [email protected])

Company Description

Traverse Health is a prominent real-world evidence provider operating across the EU and emerging markets. We specialize in developing innovative digital solutions for the healthcare and life-sciences sectors. By connecting healthcare organizations with the pharmaceutical and biotech industries, we unlock the transformative power of patient data to deliver real-world value. Our mission is to enhance healthcare decision-making and improve patient outcomes through data-driven insights.

About the role

We are looking for an ML Engineer to design, build, and scale machine learning systems across a federated healthcare data platform. You will work with large-scale real-world data (RWD) from hospitals, medical devices, and clinical systems, covering both structured and unstructured sources.

Your work will span the full data-to-insight lifecycle — from automated data ingestion and transformation pipelines, to advanced analytics, predictive modeling, and extraction of clinically meaningful insights.

You will contribute to building an intelligence layer on top of healthcare data infrastructure, enabling use cases such as:

- Real-world evidence (RWE) generation
- Clinical decision support
- Patient stratification and cohort discovery
- Medical and operational insights for healthcare providers and pharma

This is a production-focused role, where you will own ML and data-driven components end-to-end — from problem framing and modeling to deployment, monitoring, and continuous improvement in real-world environments. Data & Platform Intelligence

- Design and develop ML-driven components across a federated healthcare data platform
- Build automated data pipelines for ingestion, transformation, and feature generation from heterogeneous data sources (EHR, claims, devices, registries)




- Work with common data models (e.g., OMOP) and support scalable data standardization

Machine Learning & Advanced Analytics

- Develop predictive models for risk stratification, outcome prediction, and patient prioritization
- Build models for pattern detection, anomaly detection, and clinical event forecasting
- Apply ML to both structured data (tabular, time-series) and unstructured data (clinical notes, reports, device data)
- Implement feature engineering pipelines for temporal, longitudinal, and irregular datasets

Unstructured Data & AI

- Develop pipelines for extracting structured signals from unstructured clinical text (e.g., physician notes, reports)
- Apply NLP, embedding models, and retrieval-based approaches to identify clinically relevant variables and outcomes
- Contribute to building systems that reconstruct or infer missing clinical information from fragmented data

Production & MLOps

- Own model lifecycle end-to-end: training, validation, deployment, monitoring, and retraining
- Build scalable pipelines for model versioning, evaluation, and drift detection
- Integrate ML components into production systems used by clinical, research, and commercial stakeholders
- Ensure reliability, reproducibility, and auditability of models in regulated environments

Clinical & Research Collaboration

- Translate clinical and research questions into data and ML problems
- Work closely with data engineers, clinicians, and project teams to ensure outputs are medically meaningful and actionable
- Support development of analytics and insights used in RWE studies, dashboards,



and research deliverables

REQUIRED EXPERIENCE We are looking for an engineer who has built and deployed ML systems in production environments, ideally working with complex, real-world datasets.

Core ML & Engineering

- Strong Python experience with ML libraries (scikit-learn, XGBoost/LightGBM, or similar)
- Experience with structured and/or time-series data (forecasting, classification, anomaly detection, etc.)
- Experience with data pipelines and feature engineering at scale
- Experience deploying ML systems into production (monitoring, retraining, performance tracking)
- Strong SQL and data manipulation skills (Pandas, NumPy)
- Familiarity with containerized environments (Docker)

Data & Systems Thinking

- Experience working with heterogeneous, imperfect, or real-world datasets
- Understanding of end-to-end data pipelines (ingestion → transformation → modeling → serving)
- Experience with workflow orchestration tools (Airflow, Prefect, or similar)

Healthcare / Regulated Environments

- Experience in regulated or high-reliability environments (healthcare, finance, etc.)
- Familiarity with healthcare data formats and standards (EHR, HL7/FHIR, OMOP) or ability to quickly adapt to domain-specific data

TECH STACK Technologies used in this role (or similar equivalents):

- Python
- scikit-learn / XGBoost / LightGBM
- Pandas / NumPy
- SQL
- Docker
- MLflow / Weights & Biases (or similar)
- Airflow / Prefect
- Cloud platforms (AWS / GCP / Azure)

NICE TO HAVE

- Experience with NLP or working with unstructured clinical text
- Experience with real-world data (RWD) / real-world evidence (RWE)
- Familiarity with OMOP / OHDSI ecosystem
- Experience with real-time or near real-time data pipelines
- Experience in healthcare analytics, clinical research, or digital health platforms
- Experience working in hybrid rule-based + ML systems
- Experience working in hybrid rule-based + ML systems

📌 ML ENGINEER | Healthcare Data Platform · AI & Analytics (Barcelona)
🏢 Traverse Health
📍 Barcelona