Adithya Samavedhi

Software Developer

Goldman Sachs

Biography

I am currently working as a software developer at Goldman Sachs exploring cutting-edge technologies. My fascination for computer science opriginates from my passion to solve problems and puzzles. Something about our problem solcing ability as humans amazes me. For the same reason, I’ve continuously explored the field of machine learning in the hope to see if they could match human intelligence. In particular, the evolution of human communication has left me enthralled and I’m currently exploring natural language processing technologies to help computers mimic this.

Download my resumé.

Interests

Natural Language Processing
Artificial Intelligence
Machine Learning
Information Retreival

Education

B.E. Computer Science, 2021

Birla Institute of Technology & Science, Goa Campus
Telangana State Board, 2017

FIITJEE, Saifabad
CBSE, 2015

CHIREC International

Experience

Software Developer

Goldman Sachs

Jul 2021 – Present Bengaluru

Part of Middleware Engineering team
Working on projects handling over 4000 hosts of the firm
Technologies used: Python, Java, Prometheus, Celery

Research Intern

Virginia Polytechnic Institute and State University

Nov 2020 – Dec 2020 Remote

Implemented four baseline neural network models for long document comparison : HAN, SMITH, DSSM, ARC-1
Created two benchmark datasets for long document comparison from Wikipedia repository, ACL AAN.
Co-authored a long research paper

AI Intern

Couture AI

Nov 2020 – Dec 2020 Remote

Designed a video recommendattion system to provide personalized recommendations to users
Designed pipeline to incoporate candidate generation to identify candidate videos for the recommendation systems
Incorporated over 20,000,000 videos to generate recommendations for over 6,000,000 users

Software Developer Intern

Goldman Sachs

May 2020 – Jun 2020 Remote

Worked as part of the Middleware Engineering team of the firm
Technologies used: Python, Postgres, cron

Software Developer Intern

Telangana e-Governance

Nov 2020 – Dec 2020

Designed a static website to showcase the projects of Telangana Life Sciences corporation
Worked along a team of 5 to survey, design and implement the website
Technologies used: HTML, CSS, Javascript

Projects

Designing Protective Measures against Malware Attacks

Devised a gradient based, greedy attack strategies to modify malicious applications to fool detection systems
Designed a novel defensive strategy to protect detection systems from malware attacks
Validated the strategies for twelve classification algorithms against 50,000 android applications

Detection of Malaria from Segmented Human Cell Images

Built detection models using convolutional neural networks in Pytorch implementing a custom architecture and transfer learning from state-of-art models

Empirical Analysis of Student Feedback (Confidential Project)

Pre-processing raw feedback data collected across 10 streams, 200+ courses, 100+ faculty
Implementing sentiment analysis models, clustering objective responses, deriving inferences through knowledge graphs

Profiling Fake News: Learning the Semantics and Characterisation of Misinformation

Proposed Fake News detection model using extracted syntactic, semantic, temporal features
Evaluated the hypothesis against four benchmark datasets of varying article lengths

Supervised Contrastive Learning for Interpretable Long Document Comparison

Recent Publications

Quickly discover relevant content by filtering publications.

Hemant Rathore, Adithya Samavedhi (2021). Are Malware Detection Models Adversarial Robust Against Evasion Attack?. INFOCOM'22.

Akshita Jha, Jaideep Chandrashekar, Vineeth Rakesh, Adithya Samavedhi and Chandan K Reddy (2021). Supervised Contrastive Learning for Interpretable LongDocument Comparison.

Hemant Rathore, Adithya Samavedhi, Sanjay K. Sahay and Mohit Sewak (2021). Robust Malware Detection Models: Learning from Adversarial Attacks and Defenses.