ROLE
– Explore spatial resolution enhancement of hyperspectral data, starting with RGB/visual bands and later extending to full HSI stack enhancement while preserving spectral integrity.
– Develop highly accurate cloud, water, shadow, snow, haze, and unusable-pixel masks at L1A, and L1C stages.
– Build AI-assisted methods for manual QA/QC reduction, image quality flagging, failure classification, and automated decision support.
– Investigate AI-based methods for noise detection, stripe detection, bad-pixel identification, blur/sharpness assessment, and artifact classification.
– Develop models that can identify patterns between image quality and capture conditions such as geography, temperature, illumination, viewing geometry, season, clouds, and processing status.
– Explore AI/LLM-based systems for IPR query management, processing-status search, failure summarization, metadata interpretation, and internal operational intelligence.
– Work closely with radiometric, geometric, atmospheric correction, product, QA/QC, and pipeline teams to convert research ideas into usable processing modules.
– Maintain scientific discipline by ensuring that AI-based corrections do not compromise radiometric, spectral, spatial or geometric integrity.
– Build validation frameworks, benchmark datasets, model evaluation metrics, and confidence scores for all AI-assisted correction workflows.

REQUIREMENTS
– Strong background in computer vision, deep learning, image processing, and scientific coding.
– Experience with satellite, aerial, hyperspectral, multispectral, SAR, medical, or other scientific imaging data.
– Hands-on experience with PyTorch/TensorFlow, OpenCV, NumPy, Rasterio/GDAL, and large image datasets.
– Understanding of segmentation, super-resolution, denoising, anomaly detection, classification, and self-supervised learning.
– Ability to design experiments, evaluate models scientifically, and communicate results clearly.
– Strong interest in building practical AI systems for real-world image processing pipelines.
– Experience with hyperspectral or multispectral remote sensing data.
– Knowledge of radiometric correction, atmospheric correction, geometric correction, or satellite image quality assessment.
– Experience with foundation models, vision transformers, diffusion models, self-supervised learning, or LLM-based workflow tools.
– Experience creating annotated datasets, active learning pipelines, or human-in-the-loop QA systems.
– Publications or postdoctoral research experience in computer vision, remote sensing, or scientific image processing.