About Me

Irish Mehta - Machine Learning Engineer and AI Researcher

I'm a developer with three years of industry experience in building Machine Learning models. I have a solid background in end-to-end development, with a focus on building generalizable, scalable and efficient solutions.

I take pride in my ability to innovate and think out of the box. I am an expert user of Python and I am familiar with a wide range of tools and frameworks to solve any problem at hand. For me, tools are mediums to put creative throughts into actions. I am a strong advocate of open source and I feel that sharing knowledge is the best way to contribute to the community.

I am currently pursuing my Master's in Computer Science at Arizona State University, where my goal is to upskill myself in all the subfields of AI. This includes Classical ML, Generative AI, Natural Language Processing, Computer Vision, and Robotics. Parallel to academics, I am working as a Data Scientist and Researcher at different laboratories to apply learned theory to real-world problems.

My Journey

Aug 2024 – May 2026

M.S. Computer Science

@ Arizona State University
Natural Language Processing •
Topics in Generative AI •
Cloud Computing •
Data Mining •
Semantic Web Mining •
AI in Robotics •
Data systems for ML •
Data Processing at Scale•
Knowledge Representation •
Oct 2023 – Jun 2024

Machine Learning Engineer

@ O9 Solutions
Python • Spark • Supply-Chain ML • Client Interaction
Oct 2022 – Oct 2023

Machine Learning Engineer

@ Head Digital Works
MLOps • AWS • Micro-services • Real-time ML
Jun 2021 – Sep 2022

Associate Data Scientist

@ Head Digital Works
XGBoost • Fuzzy Logic • ETL
2017 – 2021

B.E. Electronics & Communication

@ BITS Pilani

Projects

Showcasing some of my favorite work and personal projects.

Mars-Bench - Computer vision benchmark dataset for Martian features using PyTorch and Hugging Face

Mars-Bench

Python • PyTorch • Deep Learning • Computer Vision • Image Classification • Semantic Segmentation • Object Detection • Model Finetuning • Hugging Face • Benchmarking • Research

Mars-Bench brings 20 standardized datasets for classification, segmentation, and detection of Martian features like craters, cones, boulders, and frost, aiming to make evaluation consistent and to catalyze Mars‑specific foundation models.​

Adaptive Learning Platform - Adaptive learning system driven by a Multi-Armed Bandit controller to optimize question difficulty in real-time

Adaptive Learning Platform

Multi-Armed Bandit • Adaptive Learning • Reinforcement Learning • Machine Learning

An adaptive learning system driven by a Multi-Armed Bandit controller to optimize question difficulty in real-time. The architecture uses a Streamlit frontend, a Groq API-based question generator, and JSON for persistent progress saving.

DishCovery - Food discovery app using Gemini AI, Snowflake Cortex API, and Next.js

DishCovery

Python • Google Gemini AI • Snowflake Cortex API • GCP • Next.js • TypeScript • Natural Language Processing • Vector Search • Full-Stack Development

DishCovery is a food discovery app that analyzes restaurant menus and enables natural language query-based filtering of dishes and restaurants.

Silkot Silicones - Responsive website design and development using Next.js, React, and SEO optimization

Silkot Silicones

Next.js • React • TypeScript • SEO Optimization • Vercel • Web Development • Responsive Design • Frontend Development

Designed and developed a responsive website for Silkot Silicones, a leading manufacturer of silicone products. The website features a clean, modern design with a focus on usability and SEO.​

CounterEcho AI - Vulnerability-based strategic counter-narrative system using NetworkX and LLMs

CounterEcho AI

NetworkX • Graph Theory • Social Network Analysis • Counter-narratives • Louvain Algorithm • Symbolic Reasoning

A vulnerability-based strategic counter-narrative system that analyzes social network data to generate targeted counter-narratives based on user vulnerability scores.

Earnings Call RAG - Financial document analysis using Retrieval-Augmented Generation with FastAPI, LangChain, and FAISS

Earnings Call RAG

Python • FastAPI • LangChain • RAG • FAISS • Vector Databases • Embeddings • Financial AI • Document Analysis • Retrieval-Augmented Generation

Earnings Call RAG Bot is a Retrieval-Augmented Generation system designed for analyzing and querying financial documents (Currently supports earnings call transcripts)

Candidate Recommendation System - AI-powered resume ranking system that intelligently matches candidates to job requirements

Candidate Recommendation System

Python • LLMs • NLP • Resume Ranking • BERT • Embeddings • Vector Search • ReRanking

AI-powered resume ranking system that intelligently matches candidates to job requirements.

Prompt Engineering - Best practice prompts and tutorials for large language models (LLMs)

Prompt Engineering

Python • Large Language Models • LLMs • Generative AI • Prompt Engineering • OpenAI • GPT • Claude • Prompt Optimization • AI Best Practices

Best‑practice prompts and tutorials for large language models.

Machine Learning from Scratch - From-scratch implementations of classic ML and deep learning algorithms using Python, NumPy, and PyTorch

Machine Learning from Scratch

Python • NumPy • PyTorch • Deep Learning • Neural Networks • Machine Learning Algorithms • Linear Algebra • Gradient Descent • Backpropagation

From-Scratch implementations of classic machine‑learning and deep learning algorithms.

Auto Storage Categorization - NLP-powered Google Drive file organization bot using Python and Google Drive API

Auto Storage Categorization

Python • Natural Language Processing • NLP • Text Classification • Google Drive API • Document Processing • Automation • File Organization • Text Analysis

NLP‑powered bot that auto‑sorts Google Drive files into logical folders.

Movie Recommendation System - Hybrid recommender system using Python, Scikit-learn, and composite ranking algorithms

Movie Recommendation System

Python • Scikit-learn • Machine Learning • Recommender Systems • Collaborative Filtering • Content-Based Filtering • Hybrid Recommenders • Data Science

Hybrid recommender merging content clues, ratings, and composite ranking.

Predictive Modelling for Composites - Regression models for optimizing composite manufacturing parameters using Python and SciPy

Predictive Modelling for Composites

Python • SciPy • Statistical Modeling • Regression Analysis • Machine Learning • Optimization • Data Science • Predictive Analytics

Regression models to optimize composite manufacturing parameters.

Recent Updates

A chronological log of my professional journey and accomplishments.

  • Submitted my first paper at CVPR 2026 under the guidance of Dr. Hannah Kerner (Nov 2025)
  • Participated in Sunhacks 2025 to develop DishCovery, a food discovery app (Sep 2025)
  • Recieved acceptance letter for my paper at NeurIPS under the Dataset & Benchmarks track (Sep 2025)
  • Completed a summer 2025 internship at the ACME lab at ASU with Dr. Krishendu Chakrabarty towards developing efficient solutions for uncertainty estimation in deep learning models (Jun 2025)
  • Submitted my first paper at NeurIPS 2025 under the Dataset & Benchmarks track with Dr. Hannah Kerner (May 2025)
  • Completed the Spring 2025 semester with a GPA of 4.22, achieving top 5%ile in Data Intensive Systems for ML and Knowledge Representation (May 2025)
  • Started working at Decision Theater @ ASU (April 2025)
  • Started volunteering at the Kerner Lab @ ASU (March 2025)

Let's Connect!

Feel free to reach out for collaborations, opportunities, or just to say hello. I'm always open to connecting with fellow data enthusiasts and developers!

Alternatively, drop me an email at