Arun Patro Email & Phone Number

New York City

Supercharging Ramp with Applied AI

New York, United States

I am a CS student at NYU Courant. Interested in ML, NLP, Compilers and Graphics.

New York, United States

1. Branches: Built a framework to visualize advanced reasoning and planning algorithms like Tree Search with LLMs. Worked onTree-of-Thought + Reflexion style planning algorithms for objective problem solving.2. Verilog Code Gen: Explored LLMs for Verilog Code Generation, using prompting, contrained generation, execution feedback andreinforcement learning to solve the VerilogEval dataset.

Bangalore + Hyderabad

I primarily worked on ML Automation of Taxonomy Tagging at Scale. I wore many hats like Data Scientist and Machine Learning Engineer. 1. Developed and Deployed over 250+ image models for various attributes like sleeve_length, pattern, etc for over 35 product categories2. Color quantization models using Vision Transformers and K-Means Clustering3. A baseline brute force continual learning framework for periodic retraining of models. 4. Model tracking and experimentation using neptune.ai5. Deployment of batch-mode inference using Pyspark + EMR + Airflow6. Python project development using nbdev.fast.aiApart from technical work, I proactively: 1. Hosted a weekly research & talks forum 2. Mentored juniors and interns 3. Wrote blog posts4. Gave work demos and presented in org-wide forums

Hyderabad, India

A Research Intern with the "Vision for Mobility" Group under CVIT in IIIT-H. Did some research on:1. Occluded Object Detection of Traffic Signs. 2. Missing object detection

Bengaluru Area, India

Data Science for Supply Chain Inbound (March 2019 - Now) | Bangalore, India1. Style Grading: Quantized performance of a style based on similar styles for Optimal Buying2. De-duplication: Scaled de-duplication models to cover various articles3. Selection Gap: Quantify optimal style width (catalog curation density of a cluster)4. Regional Utilisation: Optimal dispatch of POs to inwarding warehousesImage Sciences (May 2017 - Mar 2019) | Bangalore, India1. AttnGAN: Generated mixed new designs using interpolation of latent vectors2. Proposed different gradient measure loss functions for estimating noise vectors in GANs

Bangalore, India

• Modeled distribution of solid shirt designs using Generative Adversarial Networks• Proposed different gradient measure loss functions for estimating noise vectors• Generated new designs using linearinterpolation and vector arithmetic on noise vectors• Improved symmetry of generated shirts by imposing symmetry conditions on the GANs

Bangalore, India

• Automated assembly process of X-Ray Tube Collets using servo motors & CCD camera• Increased precision (by 2x) of focal spot detection during assembly using canny filters• Developed a PoC for Remote Beacons that monitored the environment of the shop floor

Bangalore, India

• Developed add-on modules to convert passive industrial machines to an IoT device• Supported multiple sensor and actuator integrations using USB, WiFi and BLE

Master Of Science - Ms, Computer Science

Dual Degree - B.Tech And M.Tech, Electrical Engineering