Vijish Madhavan
Machine Learning Engineer at vijishmadhavan.com
Chennai, Tamil Nadu, India
Summary
🤩
RockstarVijish Madhavan is a Machine Learning Engineer based in Chennai with six years of hands-on experience building deep learning solutions for image processing and production-ready demos. He’s a practical generalist who leverages Python, PyTorch and fastai to design and train models—examples include a ResNet34-based line art generator and a tattoo deinking pipeline that ships with a Gradio app for public access. His career blends remote deep-learning roles and technical writing, reflecting both implementation depth and the ability to communicate ML work clearly. Running his own engineering site and active GitHub indicates a maker mentality and a focus on deployable, user-facing ML tools. Notably, he pairs creative computer-vision projects with practical deployment skills, making research-style models accessible to end users.
5 years of coding experience
1 year of employment as a software developer
English, Hindi, Tamil, Malayalam
Stackoverflow
13reputation
468reached
0answers
3questions
Github Skills (20)
pytorch10
python10
image-processing10
machine-learning10
mask-rcnn10
fastai10
deep-learning10
faster-rcnn10
computer-vision10
generative-art9
gradio9
google-colab8
google-colaboratory8
stable-diffusion8
rvest6
Programming languages (4)
Github contributions (5)
vijishmadhavan/ArtLine
Nov 2020 - Aug 2022
A Deep Learning based project for creating line art portraits.
Role in this project:
ML Engineer
ML EngineerContributions:163 commits, 1 PR, 61 pushes in 1 year 9 months
Contributions summary:Vijish primarily worked on the `Train.ipynb` file, which includes code related to edge detection and defining an architecture using ResNet34. They are importing and utilizing various machine learning libraries like PyTorch, fastai, and torchvision. The code involves defining a FeatureLoss function, suggesting the user is focused on training a model related to the project's deep learning goals.
pythonartline-artgenerative-artdeep-learning
vijishmadhavan/SkinDeep
Apr 2021 - Aug 2022
Get Deinked!!
Role in this project:ML Engineer
ML EngineerContributions:194 commits, 4 PRs, 155 pushes in 1 year 4 months
Contributions summary:Vijish primarily worked on a machine-learning project focused on image processing, specifically for tattoo removal. Their contributions involved modifying and training a deep-learning model, as evidenced by changes in a Jupyter Notebook (SkinDeep_Train.ipynb) that includes code for image transformations, feature extraction, loss functions, and model training using fastai. Additionally, the user created a Gradio app (app.py) to allow the user to upload the image and run the model. The user also worked to ensure the model can be accessed with a public URL.
pytorchimgurpythondeep-learningmachine-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.