Your Mission

We are scientists,doctors, techies and humanity lovers, with the mission of pioneering real time precision neurology to cure brain-related disorders. INBRAIN harnesses the extraordinary material properties of Graphene, the world’s thinnest and nobel-prize winning material, to build high resolution neural systems. Our mission is to decode and modulate neural networks to restore people's lives. The Principal MLOps Architect will design and own the end-to-end model lifecycle architectureand governance framework that enables INBRAIN's data scientists and ML engineers to take adaptive neurostimulation and Brain-Computer Interface models from research into regulated clinical products. The role defines how models are developed, versioned, validated, packaged, released, monitored and updatedacross cloud, smartphone and embedded runtimes. It establishes the MLOps pipelines, validation gates, traceability and evidence required to ensure that every model release is reproducible, controlled and aligned with the intended clinical use. It works closely with the Software team, which owns and maintains the underlying model runtime infrastructure. The role bridges MLOps engineering with medical-device design-control practice: it defines how models are versioned, validated, and promoted,



and builds the change-control framework(aligned with a PCCP-style approach) that governs how adaptive, continuously-learning models can be safely updated post-deployment. This is afoundational, cross-functional role within the Data Intelligence team. It works closely with Data Scientists, ML Engineers and Data Engineers to establish reproducible model development and delivery practices. The role partners with Clinical, Regulatory and Product teams to translate clinical objectives, intended use and regulatory requirements into model lifecycle controls. It collaborates with Systems Engineering to ensure models meet system-level requirements and with Software Engineering to define deployment interfaces, runtime requirements and release processes across cloud, smartphone and embedded environments. What You'll Do

Main Responsibilities: Design and own the model lifecycle traceability framework, linking every model version to its source code, training datasets, data provenance, preprocessing and feature definitions, training configuration, evaluation results, risk assessments and applicable clinical evidence. Ensure that model artifacts and their supporting evidence are reproducible and retrievable throughout the product lifecycle.

#J-18808-Ljbffr

📌 Machine Learning Operations Architect (with medical device experience) (Barcelona)
🏢 Inbrain
📍 Barcelona