Research Engineer
13 days ago
Barcelona
Company Description IOMED operates a Data Space Platform powered by AI designed to activate healthcare data for secondary use while ensuring compliance with data protection. Utilizing Natural Language Processing, the platform processes both structured and unstructured clinical data, enabling transformation into an interoperable OMOP Common Data Model without data leaving a hospital’s in-house systems, thanks to its Federated Data Model. IOMED’s innovative approach bridges the gap between raw clinical data and standardized formats for meaningful analysis in Data Spaces. With a focus on data security, IOMED's mission is to be a trusted ally for healthcare organizations, fostering the future of data-driven healthcare. We are looking for a NLP Engineer / Incident Analyst to support the daily operation and continuous improvement of our Natural Language Processing (NLP) systems applied to clinical data. This role sits at the intersection of data science, NLP, and operations. You will focus on diagnosing and resolving issues in production NLP pipelines, analyzing data outputs, and improving system reliability and efficiency. You will play a key role ensuring that clinical text is transformed into high-quality structured data used for research and AI applications. Diagnose and resolve incidents affecting NLP data extraction pipelines. This will imply: working closely with other teams, querying our clinical databases, creating tests for our NLP pipeline, and debugging such pipeline. Work closely with data quality, engineering, and clinical teams to improve system performance. Querying our clinical databases to retrieve clinical notes, examine them, create tests, detect errors and inconsistencies in our NLP results and find patterns. Debug and improve our NLP system, including rule-based and hybrid (rules + models) processing pipelines. Implement fixes and validate improvements through testing. Continuously monitor data quality and help improve system robustness over time. Demonstrated proficiency in Python and SQL and working with textual data through professional experience or formal education. Excellent knowledge of Python , regexes and pattern-matching. Strong SQL skills and experience with git . Experience working with Unix environments (linux and/or Mac). Passion for debugging and testing. Comfortable with reading other people’s code, debugging it and proposing fixes. Some experience with text processing/analysis. Ability and motivation to explore datasets deeply and learn from data patterns. Experience and interest in working with healthcare or clinical data is a plus but not required. Interest in health/clinical data. Permanent contract. ~ A very unique project and mission, working with clinical data and potentially contributing to clinical research and improving lives. ~ Flexible remuneration with restaurant tickets, transport tickets, nursery, training, and medical insurance (if based in Spain). ~ Flexible schedule and hybrid/remote working model. ~