Aditya Muchak

Aditya Muchak

Sophomore at IIT MADRAS

Maharashtra, IndiaMachine Learning and Artificial Intelligence
8roles
41skills
5education
3credentials

About

I am currently pursuing a degree in Chemical Engineering at IIT Madras, where I am passionate about both technical innovation and personal growth. With a solid foundation in C++ and Python programming, I enjoy applying computational methods to solve complex engineering challenges and streamline processes. Beyond academics, I channel my enthusiasm and teamwork skills as a proud member of the NSO Hockey team at IIT Madras. This experience has taught me the value of discipline, collaboration, and resilience—qualities that I bring to every project and initiative I undertake. Driven by clear goals and an unwavering commitment to excellence, I consistently approach my work with energy and enthusiasm. I am eager to connect with professionals and peers who share a passion for engineering, technology, and collaborative growth.

Experience

Project Member

Nirmaan IITM

8 mos · India

Student Mentor

Saathi, IIT Madras

9 mos · India

Alumni club Coordinator

Chemical Engineering Society , IIT Madras

1 yr 3 mos · India

As the Coordinator of the Chemical Engineering Alumni Club at IIT Madras, I will be responsible for fostering engagement between alumni, students, and faculty. My role involves organizing networking events, mentorship programs, and industry interactions to strengthen our alumni network. I aim to enhance collaboration through knowledge-sharing initiatives, career guidance sessions, and alumni reunions. By leveraging the expertise of our distinguished alumni, I hope to create meaningful opportunities for both current students and graduates, ensuring a strong and supportive professional community.

Coordinator

Chemical Engineering Society , IIT Madras

6 mos

Being a Coordinator of the Chem Alumni Club ,Acted as a bridge between faculty, alumni, and students, fostering stronger professional and personal connections within the Department of Chemical Engineering. Also had experience in engaging with new startups in NIRMAAN iit madras the pre-incubator as a coordinator.

Manager

E-Cell IIT Madras

11 mos

Oversaw end-to-end content strategy, including articles, reports, startup profiles, and thought pieces on entrepreneurship and innovation. Initiated and secured podcast collaborations with industry leaders, including Farzad Palia (CEO, Viacom18 Digital Ventures), strengthening E-Cell’s industry network.

Associate Manager

E-Cell IIT Madras

5 mos · India

Associate Manager – Editorial and Research Team, e-cell IIT Madras In this role, I am a part dynamic team of researchers and editors to develop and disseminate high-quality, industry-relevant content that supports the entrepreneurial ecosystem at IIT Madras. My responsibilities include: Content Strategy & Management: Overseeing the creation, curation, and publication of articles, research reports, and multimedia content to ensure alignment with the latest trends and insights in the startup world. Project Coordination: Managing multiple research and editorial projects simultaneously, ensuring timely delivery while maintaining rigorous quality standards.

ML Intern

Happieloop Technologies

Performed exploratory data analysis using Pandas and Matplotlib; implemented image classification using a pre-trained deep learning model with transfer learning; built and visualized a K-Means clustering model with feature scaling and optimal K selection.

Research Intern

Assoc. Prof. Himanshu Goyal

Modeled a Steam Methane Reforming 3D reactor in 1D Python to simulate and optimize hydrogen yield. Engineered a Python/C++ pipeline using Numba JIT that achieved a reported 1700× speedup. Translated 15+ research papers into production-grade algorithms solving 5,600+ coupled stiff ODEs with 99.9% stability.

Education

Indian Institute of Technology, Madras

Bachelor of Technology, Chemical Engineering

Jul 2024 - Jun 2028

8.87/10 CGPA

Orchid English school

Class-10

[object Object]

Orchid junior college

Science

[object Object]

Orchid Junior College

Class X

2022

91.17%

Orchid English College

Class XII (Maharashtra State Board)

2024

96.8%; topped college in 12th grade with 91.17% in HSC board

Skills

CommunicationAnalytical SkillsMachine LearningNumerical AnalysisReinforcement LearningUnsupervised LearningSupervised LearningComputational MathematicsTensorFlowMATLABPandas (Software)Python (Programming Language)Text-to-Image GenerationPythonC++NumPyPandasPyTorchScikit-LearnMatplotlibAspen PlusData Structures and AlgorithmsObject-Oriented ProgrammingMachine Learning AlgorithmsJupyter NotebookVS CodeKerasNLTKKeras TunerHugging Face DiffusersStreamlitCUDAONNXPybind11Numba JITLinear AlgebraProbability and StatisticsDeep LearningNatural Language ProcessingComputer VisionOptimization

Projects

Text to image convertor

This is a local, offline text-to-image generation application built using Stable Diffusion v1.4 and Streamlit. This tool allows users to generate high-quality images from text descriptions with granular control over inference steps and guidance scale.

AI Ripeness Prediction & Supply Optimization

Built an end-to-end banana ripeness prediction system using PyTorch and a fine-tuned ResNet18 model optimized with ONNX for low-latency inference. Designed a supply chain optimization engine as a Capacitated Vehicle Routing Problem using a high-performance C++ solution with Pybind11 integration.

Dual-Domain Image Restoration (Restormer + FT)

Augmented the Restormer architecture with Fourier Transform layers to process spatial features and filter high-frequency noise. Engineered a custom Cosine Annealing learning-rate scheduler with 50-epoch warm restarts in PyTorch.

Generative AI Pipeline Architect – Stable Diffusion Text-to-Image Web App

Built a real-time generative AI text-to-image application using PyTorch, Hugging Face Diffusers, and Streamlit. Optimized VRAM utilization and latency through dynamic CUDA hardware routing, FP16 processing, and state caching. Created a data provenance pipeline storing multi-image outputs and hyperparameter metadata in JSON for experiment reproducibility.

SMS Spam Detection

Built an LSTM-GRU hybrid deep learning model using TensorFlow and Keras, achieving 97.8% test accuracy and a 0.985 AUC score. Applied tokenization, lemmatization, stopword removal, model tuning, and precision, recall, F1-score, and ROC-AUC evaluation.

Volunteering

Volunteer

Saarang, IIT Madras

Jan 2025 - Jan 2026 · 1 yr 1 mo

Volunteer

Placement & Internship Cell, IIT Madras

[object Object]

Crowd Management Volunteer

Saarang

2024

Mentor

Saathi, IIT Madras