Project Scientist, Computational Biology

Sudha Gopalakrishnan Brain Centre (SGBC); Chennai District; On-site; INR 1,200,000 - 2,300,000; Full time

Job summary

The Centre for 3D Cancer Omics at IIT Madras invites a lead computational scientist to develop digital pathology architectures and multi-omics integration for precision oncology.

You will design and deploy scalable workflows, work with clinicians and bioinformaticians, and mentor junior researchers in HPC and cloud environments. The role is full-time, on-site, and offers a pathway to impactful cancer research in India.

Qualifications

• Ph.D. in Computational Biology, Bioinformatics, Data Science or a related field.
• Minimum 2 years post-doctoral or industry experience in end-to-end data analysis and deploying computer vision workflows for digital pathology.
• Expertise in multi-modal data integration (spatial histopathology, spatial transcriptomics, genomic variants, clinical metadata).

Responsibilities

• Lead the computational pipeline for whole-slide image processing, QC, registration and 3D tissue volume reconstruction.
• Design, implement and validate computer vision and deep learning models for cell segmentation, tissue phenotyping and spatial feature extraction.
• Integrate spatial histopathology features with spatial transcriptomics, genomics, longitudinal clinical data, and liquid biopsy dynamics.
• Build scalable, containerized workflows (Python, R, Docker, Nextflow) for HPC and cloud environments.
• Collaborate with clinicians, pathologists, wet-lab scientists and bioinformaticians to translate findings into hypotheses.

Skills

AI/ML development

Computer vision

3D tissue modeling

Data integration

Education

PhD in Computational Biology/Bioinformatics/Data Science

Tools

PyTorch/TensorFlow

QuPath

OpenSlide

MONAI

Docker/Nextflow

Job description

The Centre for 3D Cancer Omics at IIT Madras is a Focused Research Organization dedicated to advancing multidisciplinary digital tissue mapping and high-resolution histopathology in oncology. Operating at the intersection of clinical research, tissue imaging, molecular biology and computational science, we decode complex tumor microenvironments at scale. Our infrastructure integrates 3D histology, multiomics, spatial biology and liquid biopsy pipelines, with a focus on the unique genomic and clinical landscapes of Indian cohorts.

Workplace: On-site

Type: Full-time

Role Summary

Lead the development of computational architecture for digital pathology, multi-omics integration and spatial tissue modeling, turning complex tumor microenvironment data into actionable insights for precision oncology.

Key Responsibilities

• Lead the computational pipeline for whole-slide image (WSI) processing, QC, registration and 3D tissue volume reconstruction
• Design, implement and validate computer vision and deep learning models for cell segmentation, tissue phenotyping and spatial feature extraction
• Integrate spatial histopathology features with spatial transcriptomics, genomic mutations, longitudinal clinical data, liquid biopsy dynamics and peripheral biomarkers
• Build scalable, reproducible, containerized workflows (Python, R, Docker, Nextflow) for HPC and cloud environments
• Work with clinicians, pathologists, wet-lab scientists and bioinformaticians to turn findings into biological hypotheses

Required Qualifications

• Ph.D. in Computational Biology, Bioinformatics, Data Science or a related discipline, with a focus on solid tumor histopathology and molecular genomic data analysis
• Minimum 2 years of post-doctoral or industry experience in end-to-end data analysis, AI/ML development and deploying computer vision workflows for digital pathology
• Expertise in multi-modal data integration (spatial histopathology, single-cell/spatial transcriptomics, genomic variants, clinical metadata)
• Proficiency in PyTorch/TensorFlow, QuPath, OpenSlide, MONAI, and Docker/Nextflow on HPC

Preferred

• Experience combining histopathology and spatial omics with liquid biopsy dynamics and longitudinal clinical datasets
• Deep learning for automated WSI feature extraction and 3D tissue reconstruction
• Scalable pipeline development and use of open-source pathology tools