Data Scientist, Data Platform at Noetik

Experience developing image processing methods for registration, segmentation, normalization, feature extraction, or image quality control. Experience with large-scale or distributed data processing using Ray, Dask, Spark, or similar frameworks. Experience with PostgreSQL, AWS, cloud object storage, or modern data platform technologies. Experience integrating machine learning models into scientific or image processing pipelines. Experience working with biological, biomedical, or other complex sc

• Strong Python programming skills and the ability to build high-quality, maintainable software beyond notebooks and exploratory analysis.
• Experience developing data processing, scientific computing, image processing, or computational pipelines that are used and relied on by others.
• Strong understanding of data modeling, relational databases, metadata, schemas, dataset versioning, and reliable data access for downstream users.
• Experience working with image processing, computer vision, microscopy, medical imaging, remote sensing, or other large-scale image datasets. (...) # THE OPPORTUNITY

At Noetik, you’ll work alongside a highly technical, interdisciplinary team tackling hard and impactful problems. We’re looking for people who are excited to engage deeply, move with urgency, and make a meaningful impact.

KEY RESPONSIBILITIES

Courses relevant to this posting

Relevance is based on skills and concepts, not a guarantee that you qualify.

Covered skills: AI fundamentals Machine learning Python Data science Cloud User research

Skills to close: None listed

Build the skills for this job

Coming-soon courses matched to this posting: outline, waitlist, and skill path.

1. CNN Architecture for Spatial Feature Learning

Understand how convolutional layers, pooling, and receptive fields extract hierarchical visual patterns from medical images.

2. Medical Image Preprocessing and Normalization

Prepare clinical images by handling artifacts, standardizing inputs, and preserving diagnostic signal.

3. Training CNNs on Limited Clinical Datasets

Apply transfer learning, data augmentation, and regularization to build robust models from small labeled datasets.

4. Classification, Segmentation, and Detection Tasks

Implement CNNs for different clinical tasks including diagnosis, lesion boundary detection, and anatomical measurement.

5. Clinical Evaluation Metrics and Validation

Measure model performance using sensitivity, specificity, ROC curves, and clinically meaningful thresholds.

6. Addressing Bias and Distribution Shift

Identify and mitigate dataset bias, demographic disparities, and performance degradation across clinical sites.

7. Deploying CNNs in Clinical Workflows

Integrate imaging models into healthcare systems with appropriate decision support, explainability, and governance.

Other verified postings in the same role family or with overlapping skills.