Junior Ai Developer For Medical Imaging

The Centro Nacional de Investigaciones Cardiovasculares Carlos III (F.S.P) (CNIC) has been conceived to develop research of excellence, competitive and of international relevance in relation to cardiovascular diseases. The CNIC is a research center of 24,000 m 2 , located in Madrid, with more than 6,000 m 2 for laboratories equipped with a state-of-the-art infrastructure and equipment.
CNIC leads the Project, AI POCVUS-REACT, Artificial Intelligence-assisted point of care vascular ultrasound device for personalized cardiovascular prevention.
We are looking for two junior-level AI Developers with expertise in developing models for medical imaging applications. You will work on the development, optimization, and deployment of AI models, with a focus on improving the accuracy and efficiency of image analysis tools used in healthcare.
Functions:
Develop, train, and optimize deep learning models for analyzing medical images.
Integration of AI/ML models for real-time analysis and decision-making.
Preprocess large datasets, perform data augmentation, and fine-tune model architectures for improved performance.
Collaborate with medical professionals and researchers to understand domain-specific requirements.
Optimize models for deployment in real-world applications, considering efficiency, speed, and accuracy.
Document model development, experiments, and results for reproducibility.
Contribute to the development of tools and pipelines for data processing, model training, and evaluation.
Learning and supporting senior developers, model development, preprocessing, and working on well-defined tasks.
Mandatory Requirements:
Bachelor's degree in Computer Science, Biomedical Engineering, Data Science, or a related field.
Valuable Requirements:
C1. Knowledge and/or experience in Python.
C2. Knowledge and/or experience in AI/ML Integration (e.g., PyTorch) for building and training deep learning models.
C3. Knowledge and/or experience in Machine Learning. Solid understanding of key ML concepts, including supervised/unsupervised learning, CNNs (Convolutional Neural Networks), and image segmentation/object detection.
C4. Knowledge and/or experience in Data Handling. Experience with medical imaging formats like DICOM and using libraries such as OpenCV, PIL, or SimpleITK.
C5. Knowledge and/or experience in Deep Learning. Knowledge of deep learning architectures such as YOLO, UNet, non-UNets, GANs, etc.
C6. Knowledge and experience in Version Control. Familiarity with Git for code management and collaboration.
C7. Knowledge and/or experience in AI development or relevant projects. Professional experience not mandatory, academic projects and internships are acceptable.
C8. Underrepresentation of gender by category, in accordance with Action S1 of the 2021-2024 Equality Plan, POSITIVE ACTION IN CALLS FOR POSTS.
C9. Interview (it will be partially conducted in English).
We offer:
Competitive salary (estimated annual salary: 52.261,93 € + 25% Variable).
Consolidated Research Center of international scientific relevance.
Access to an infrastructure and advanced technologies.
Integration into an excellent scientific environment.
Immediate incorporation.
Selection Plan:
The RESOLUTION OF THE SECRETARIAT OF STATE FOR PUBLIC FUNCTION APPROVING THE COMMON ACTION CRITERIA IN THE SELECTIVE PROCESSES OF STATE PUBLIC SECTOR ENTITIES of April 11, 2022, establishes in point 6.1 that "Unless a specific regulation provides for the selective contest system, the selective system will be the contest-opposition."
In the case of CNIC, the specific regulations approved by the Foundation's board of trustees establish a selective competition system with an interview phase.
At least 3 candidates with the highest score (as long as they reach the minimum of 65 points as a sum of evaluation criteria (C1-C7) will be interviewed. The candidate with the highest score will be hired given the total score (C1-C8) is higher than 75 points.
Composition of the Selection Commission:
Group Researcher with high expertise in AI.
Research Office Coordinator.
HR member.
The CNIC guarantees, within its scope of action, the principle of equal access to employment, and may not establish any direct or indirect discrimination based on grounds of origin, including racial or ethnic origin, sex, age, marital status, religion or beliefs, political opinion, sexual orientation and identity, gender expression, sexual characteristics, trade union membership, social status, language within the State and disability, provided that the workers are fit to perform the work or job in question.
By participating in the selection process, the participant accepts that their data appear in the public resolutions of the selection process. Such resolutions (provisional list of admitted and excluded, definitive list of admitted and excluded and resolution of the process) are published on the CNIC website.
Scoring Criteria:
C1 . Knowledge and/or experience in Python (Experience will be assessed as a whole on the basis of the time/specialty ratio or according to the number of hours of accredited training). 15%
C2 . Knowledge and/or experience in AI/ML Integration (e.g., PyTorch) for building and training deep learning models (Experience will be assessed as a whole on the basis of the time/specialty ratio or according to the number of hours of accredited training). 10%
C3 . Knowledge and/or experience in Machine Learning. Solid understanding of key ML concepts, including supervised/unsupervised learning, CNNs (Convolutional Neural Networks), and image segmentation/object detection (Experience will be assessed as a whole on the basis of the time/specialty ratio or according to the number of hours of accredited training). 10%
C4 . Knowledge and/or experience in Data Handling. Experience with medical imaging formats like DICOM and using libraries such as OpenCV, PIL, or SimpleITK (Experience will be assessed as a whole on the basis of the time/specialty ratio or according to the number of hours of accredited training). 10%
C5 . Knowledge and/or experience in Deep Learning. Knowledge of deep learning architectures such as YOLO, UNet, non-UNets, GANs, etc. (Experience will be assessed as a whole on the basis of the time/specialty ratio or according to the number of hours of accredited training). 10%
C6 . Knowledge and/or experience in Version Control. Familiarity with Git for code management and collaboration (Experience will be assessed as a whole on the basis of the time/specialty ratio or according to the number of hours of accredited training). 10%
C7 . Knowledge and/or experience in AI development or relevant projects. (Experience will be assessed as a whole on the basis of the time/specialty ratio or according to the number of projects in the field). 10%
C8 . Underrepresentation of gender by category, in accordance with Action S1 of the 2021-2024 Equality Plan, POSITIVE ACTION IN CALLS FOR POSTS. 5%
C9 . Interview (it will be partially conducted in English). 20%
In the event of absence of any of the evaluators, an alternate evaluator of the same area will be appointed.

#J-18808-Ljbffr