Chinmay Raut
Chinmay Raut

Project Research Scientist · Health Informatics and Imaging Lab, IIT Madras

Notebook — lab record

Curriculum Vitae

Download PDF

Education

Indian Institute of Technology Madras

Dual Degree Programme - B.Tech in Engineering Design & M.Tech in Biomedical Design · Chennai, India

Jul 2018 – May 2023

  • CGPA: 8.91/10
  • Graduated in the top 5% of the class
  • Relevant coursework: Applied Statistics, Mathematical Foundations of Data Science, Life Sciences, Human Anatomy, Physiology & Biomechanics, Medical Image Analysis, Signals and Systems, Digital Signal Processing, Design of Monitoring and Diagnostic Systems.

Work Experience

Project Research Scientist - 1

Health Informatics and Imaging Lab, IIT Madras

Oct 2025 – Present

  • Developed PS-MAE for an ICMR-funded breast cancer research. Designed its masked-pretraining objective using clinical evidence that peritumoral tissue contains metastasis-related signals. The encoder outperformed state-of-the-art methods under linear probing and on a class-imbalanced external cohort. First-author manuscript under review at IEEE JBHI.
  • JEPA-distilled USFMAE into a TinyViT and added an auxiliary radiomics-prediction objective to capture information beyond the teacher embeddings. The 15× smaller encoder outperformed state-of-the-art classification models, retained performance on an external dataset, and performed best under linear probing, demonstrating inherently separable representations. Coordinated with clinicians to adapt the system for on-site deployment.
  • Built an agentic system for the MICCAI 2026 CHIMERA Challenge, awarded 2nd place, that combined histopathology, clinical, and molecular evidence for prostate-cancer risk assessment. The system reported its confidence, influential variables, and policy trace, making each decision auditable.
  • Evaluated breast-ultrasound segmentation across Indian, Polish, and Egyptian cohorts, identifying performance gaps caused by acquisition differences and population-linked morphology. Developed adaptive wavelet normalization to reduce this cross-cohort gap. Manuscript under review at BSPC.
  • Mentored undergraduate and MS students, conducted tutorials on vision transformers, LLMs, Linux, and remote computing, and administered the lab's GPU infrastructure, including user access, storage, software environments, drivers, and GitHub repositories.
Product Analyst

Ather Energy, Bangalore, India

Aug 2023 – Oct 2025

  • Analysed large-scale telemetric datasets from 400,000+ connected electric scooters each having 100+ IoT sensors transmitting 800 GB+ data daily, extracting insights on riding style, charging patterns, smart features usage and vehicle utilisation across various demographic groups in India, Sri Lanka and Nepal.
  • Built an ETL pipeline using PySpark and Clickhouse SQL for product analytics. Designed and monitored product metrics; conducted regular analysis on their movement to generate actionable product and business insights.
  • Performed population modelling for ride assist features, correlating adoption and engagement of a feature to other ride metrics and behavioural patterns to build adaptive intelligent algorithms, which led to 12% improvement in adoption.
  • Developed a LangChain-based LLM tool to categorise user feedback from multiple channels, unifying qualitative data with quantitative metrics.
Undergraduate Researcher

iNSPIRE Lab, IITM, Chennai, India

May 2021 – Dec 2021, Jul 2022 – May 2023

  • Worked on developing tools and algorithms for planning needle trajectories for minimally invasive neurosurgeries.
  • Implemented and trained a UNet-based network architecture using Pytorch for tumour segmentation using a publicly available dataset from the BraTS challenge.
  • Utilised FastsurferCNN for cortical parcellation and MRA data for blood vessel identification to generate the environment for reinforcement learning.
  • Developed a reinforcement learning framework called Flexible Needle Path Generation, which generated 15% safer and 10% smoother curves compared to traditional path-finding algorithms like RRT*.
  • Developed a virtual reality pipeline using Slicer 3D software and an Aruco marker as an input device tool to plan linear surgical trajectories.
  • Used Unity 3D game engine to simulate environments with different lighting to generate images to train a CNN model to minimise registration error, which was utilised for a demo augmented reality app using the Vuforia engine.
Research Intern

Samsung Research Institute, Bangalore, India

Dec 2021 – Jun 2022

  • Developed a CNN model 'LiteAR' for dynamically estimating illumination for mixed reality applications using spherical harmonics for A and M series Samsung smartphones.
  • Developed an augmented reality app by incorporating LiteAR into the open-source rendering engine Filament.
  • Worked on Samsung's proprietary Neural Radiance Fields (NeRF) model utilising inverse rendering to generate 3D views from a few 2D images.

Positions of Responsibility & Volunteer Work

Teaching Assistant

Data Science: Theory & Practice, Introduction to Computation & Visualization

Aug 2022 – May 2023

  • Taught Python for data science and C for computation and graphics visualisation in the laboratory sessions for both courses.
  • Evaluated assignments and code submissions for 60+ students.
Project Management Head

Nirmaan, IIT Madras

Sep 2020 – Jun 2021

  • Led a team of 10 and managed pre-seed funding, legal support, and talent acquisition for 40+ student startups.
  • Conducted project reviews that helped 15+ teams develop an MVP.

Teaching Resource for Underprivileged Children

National Service Scheme, IIT Madras

Sep 2018 – May 2019

  • Taught mathematics and science to children from underprivileged communities in Chennai.

Technical Skills

Languages: Python, SQL, C/C++, JavaScript, HTML/CSS

Frameworks: PyTorch, PySpark, Flask, Streamlit, LangChain, LangGraph

Developer Tools: Git, Docker