Computer Vision Engineer II (Microscopy Imaging)

About the Role We are looking for a Computer Vision Engineer to design and develop custom algorithms for microscopy and biomedical image analysis. You will build end-to-end image analysis pipelines, work with cutting-edge deep learning and vision foundation models, and collaborate closely with biologists, scientists, and AI researchers to solve real-world imaging challenges.

Key Responsibilities

• Design and develop custom computer vision algorithms using Python, OpenCV, and deep learning frameworks for microscopy image analysis.
• Build end-to-end image analysis pipelines tailored to microscopy workflows, from raw acquisition to quantitative output.
• Work with diverse microscopy modalities, including Brightfield, Phase Contrast, Fluorescence, Confocal, and other light/electron microscopy datasets.
• Develop solutions for cell and tissue segmentation (including instance and semantic segmentation), cell/organelle detection, tracking, and morphological feature extraction.
• Design algorithms for image enhancement, denoising, deconvolution, and artifact correction specific to microscopy data (e.g., uneven illumination, photobleaching, low-light noise).
• Build quantitative image analysis tools for measuring cell counts, morphology, intensity, colocalization, and other biologically relevant metrics.
• Design and implement custom algorithms rather than relying solely on off-the-shelf microscopy software tools (e.g., ImageJ/Fiji, CellProfiler), where custom solutions offer greater accuracy or flexibility.
• Leverage, adapt, and fine-tune modern deep learning and vision foundation models (e.g., segmentation foundation models, self-supervised models) for microscopy-specific applications.
• Handle large-scale, high-dimensional microscopy data (multi-channel, z-stacks, time-lapse) efficiently, including preprocessing and pipeline optimization.
• Collaborate with biologists, microscopists, and AI researchers to translate experimental imaging needs into robust computational solutions.
• Evaluate, validate, and optimize machine learning and deep learning models for accuracy, robustness, and computational performance on microscopy datasets.

Qualifications, Skills & Candidate Profile

• B.E./B.Tech./M.Tech./M.S. in Computer Science, Artificial Intelligence, Computer Vision, Electronics, Electrical Engineering, Biomedical Engineering, or related disciplines.
• Freshers and experienced candidates (05 years) are welcome to apply.
• Strong programming skills in Python and hands-on experience with OpenCV.
• Good understanding of Computer Vision, Image Processing, Machine Learning, and Deep Learning, with a focus on microscopy image analysis.
• Experience implementing, training, and evaluating deep learning models using PyTorch or similar frameworks, ideally applied to cell/tissue imaging tasks.
• Familiarity with modern vision architectures such as CNNs, Vision Transformers (ViTs), segmentation models (e.g., U-Net, Mask R-CNN, Cellpose, StarDist), and vision foundation models (e.g., SAM) as applied to microscopy.
• Knowledge of cell/tissue/organelle segmentation, feature extraction, image enhancement, denoising, and custom image processing pipeline development for microscopy data.
• Hands-on exposure to microscopy imaging modalities such as Brightfield, Phase Contrast, Fluorescence, or Confocal microscopy is preferred.
• Familiarity with tissue staining image data coming from sectioning
• Experience through industry projects, academic research, internships, thesis work, or personal projects involving microscopy or cell imaging data.
• Strong analytical, problem-solving, and research skills, particularly in interpreting biological/imaging data.