Role: Computer Vision Scientist
Employment Type: Full-time
Location: India (Bengaluru office)
Work Experience: Strong background in computer vision, deep learning, image processing, and scientific coding.
Role Overview
We are looking for a highly motivated Computer Vision Scientist / Postdoctoral Scientist to explore, develop, and implement AI/ML/DL-based solutions for satellite image processing workflows within the IPR team. This role is not focused on downstream analytics, but on improving the quality, reliability, automation, and speed of core image correction and QA/QC pipelines.
The person will work at the intersection of satellite data, hyperspectral imaging, computer vision, deep learning, and scientific image correction. The role will begin with low-hanging, high-impact problems and gradually evolve toward ambitious, long-term AI-driven processing systems for hyperspectral satellite data.
Key Responsibilities
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.
Long-Term Focus Areas
Full hyperspectral spatial enhancement with spectral-preservation constraints.
AI-assisted denoising, destriping, bad-pixel detection, and artifact correction.
Scene-adaptive correction recommendations for radiometry, geometry, and atmospheric workflows.
Foundation-model or self-supervised learning approaches for hyperspectral satellite data.
Intelligent IPR assistant for pipeline monitoring, anomaly detection, and processing decision support.
Required Skills
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.
Preferred Skills
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.
Success in This Role Looks Like
Demonstrated improvement in visual quality without compromising scientific data integrity.
Reduction in manual QA/QC effort through reliable AI-assisted tools.
Accurate and production-ready masks for cloud, water, shadow, snow, and unusable regions.
New AI modules integrated into IPR workflows after proper validation.
Clear roadmap for long-term AI adoption in hyperspectral satellite processing.
Candidate Acumen: The ideal candidate is a research-oriented computer vision scientist who is excited by difficult satellite image correction problems, understands that AI must be scientifically validated, and can convert ambitious ideas into working prototypes and eventually production-ready tools.
About Pixxel
Pixxelis a space data company and spacecraft manufacturer redefining Earth observation with hyperspectral imaging. The company’s first three commercial hyperspectral satellites—Fireflies—deliver imagery at 5-meter resolution and 135+ spectral bands, providing 50x richer detail than traditional Earth observation systems and unlocking insights across agriculture, climate, energy, environment, and more.
Once fully deployed, Pixxel’s constellation of 18-24 satellites will capture imagery across up to 250 bands in VNIR and SWIR ranges, with a 40 km swath and daily global revisit capability. Pixxel’s most unique strength is its full-stack approach, integrating every layer of the value chain from satellite hardware and manufacturing to AI-powered analytics.
Pixxel’s satellite constellation is complemented by Aurora, its in-house Earth Observation Studio that simplifies satellite imagery analysis and democratises remote sensing for all. Designed to make hyperspectral data more accessible, Aurora by Pixxel combines high-frequency imagery with AI-powered tools to generate actionable insights, even for users without technical backgrounds. The third pillar of Pixxel’s ecosystem is its in-house satellite manufacturing capability. Beyond building its own spacecraft, Pixxel also provides satellite systems and subsystems to other organisations. This dual capacity sets it apart in a sector where most companies focus on either payload design or data operations, but not both.
Pixxel’s team is young but deeply mission-aligned, with a culture rooted in curiosity, speed, and long-term thinking. As the company grows its constellation and expands Aurora, the focus remains on making space-based insights practical, scalable, and genuinely helpful so that the health of the planet becomes measurable and action becomes possible.
Pixxel was the only Indian startup selected for the Techstars Starburst Space Accelerator in Los Angeles and has been recognised in TIME’s Best Inventions of 2023, Fast Company’s Most Innovative Companies, and Via Satellite’s Top Innovators list.
