Martin Chobanyan

Github LinkedIn Kaggle

Hi, you found my webpage!

I am a machine learning engineer who loves to explore new domains and solve difficult problems.

You can find more about my work and interests below.

Experience

Lead Machine Learning Engineer

Feb 2024 - Present

Machine Learning at Homes.com

I design and deploy production-grade machine learning systems that power key features across the website, including:

  • Image tagging to detect listing amenities and features
  • Amenity extraction from listing descriptions using LLMs
  • Multi-stage, product oriented image quality assessment to ensure high quality image standards

Lead Developer and Mentor

As a lead engineer, I played a key role in designing technical roadmaps for our projects and setting coding standards and best practices within our team by writing guidelines and mentoring teammates.

Senior Machine Learning Scientist

Jul 2021 - Dec 2023

Patent

At SmileDirectClub, I worked on the reconstruction, positioning, and generative modeling of 3D teeth from smartphone images and co-authored a patent in this topic.

App Launch

I was one of the key developers of the backend 2D-to-3D dental arch reconstruction model for SmileMaker Platform, an app which delivered personalized treatment plan previews for thousands of daily customers using AI-guided smartphone imaging.

Vision Transformer Pre-training

After the initial launch, I pre-trained a Vision Transformer using self-supervised learning (MAE) on over five million images collected by our app and integrated it as the backbone for our teeth segmentation model (which underlied all 3D reconstructions).

This dramatically improved segmentation robustness, especially in real-world imaging conditions (blurry and dimly lit smartphone photos), without requiring further manual annotation.

Data Scientist

Jan 2018 - Jul 2021


At GA-CCRi (now General Atomics Intelligence) I worked on government-contract research projects for maritime and aerospace activity detection using massive trajectory data sources.

I presented my work in a speaker role at the 2019 Tom Tom Applied Machine Learning Conference in a session named Points to Videos: Extracting Behavioral Information from Maritime Tracks Using Convolutional Neural Networks.

Bachelors with Distinction

Aug 2014 - Dec 2017


I graduated from University of Virginia in 2017 with a double major in Computer Science and Statistics with a focus on artificial intelligence.

Personal Projects

Visualizing Change in Neural Networks

An experiment to assess the change in feature visualizations of a neural network as it is fine-tuned to a new task

Emotion Detection with Transfer Learning

Creating an emotion detector using pre-trained computer vision models, transfer learning, and a nifty way to create a custom dataset using Google Images

Competitions

CHAMPS Molecular Prediction (Top 5% Finish)

Predicting molecular properties using graph convolutional neural networks and chemical descriptors

HPA Single Cell Classification (Top 6% Finish)

Segmenting the locations of target proteins within cell microscopy images using a Transformer-based architecture

LANL Earthquake Prediction

Predicting the next seismic event in simulated earthquake data using an ensemble of deep learning techniques