Arpan S.

CTO

Bengaluru, Karnataka, India9 yrs 1 mo experience

Highly Stable

Key Highlights

Expert in Machine Learning and NLP.
Published research in top international conferences.
Significant savings through innovative ML solutions.

Stackforce AI infers this person is a Machine Learning and NLP expert in the Fintech and SaaS sectors.

Contact

Skills

Core Skills

Machine LearningNatural Language Processing

Other Skills

Large Language ModelsHyperparameter TuningA/B TestingText MiningNLPRecord LinkageEntity MatchingElastic SearchSQLCode OptimizationSVMRandom ForestCNNLSTMNeural Networks

About

M.Tech in Computer Science and Engineering from IIT-Bombay with expertise in Data science, Machine learning and NLP. The research work done during my masters was presented in top international conferences, namely NAACL and EMNLP. Skillset: C++, Python, Tensorflow, Pytorch, sklearn, Classical ML algorithms (Support Vector Machine, Decision Trees, Regression), Deep Learning algorithms (Convolutional neural network, Recurrent neural network, Deep Neural Networks).

Experience

Stealth mode

AI Deputy Director

Aug 2024 – Present · 1 yr 7 mos

Amazon

Applied Scientist - II

Nov 2020 – Apr 2024 · 3 yrs 5 mos · Bangalore Urban, Karnataka, India

Part of Alexa NLU Team.
Training, fine tuning large language models (LLMS) for Alexa's Indian market in English, Hindi and Hinglish.
Handling out of vocabs, new language expansion, hyperparameter tuning, beta testing, A/B, deployments etc.

Machine LearningNatural Language ProcessingLarge Language ModelsHyperparameter TuningA/B Testing

American express

Research Engineer

Aug 2018 – Oct 2020 · 2 yrs 2 mos · Bengaluru Area, India

Worked on Text Mining and NLP problems as part of Unstructured data team at Amex AI labs.
Developed and deployed an ML-based pipeline for record linkage and entity-matching, a usecase
of credit fraud detection which results in an annual saving of $ 6Mn. [US Patent filed]
Implemented LSH/Elastic Search based text matching framework for entity resolution and prospect merchant identification.
Experimented and developed metrics to measure data quality from short noisy text from customer call transcripts used in downstream tasks.

Text MiningNLPMachine LearningRecord LinkageEntity MatchingElastic Search+1

Oracle

Application Engineer

Aug 2017 – Aug 2018 · 1 yr · Hyderabad Area, India

Part of Oracle-Cloud supply chain management development group
Envisaged for NLP based semantic search methods to improve upon keyword based search for Oracle's B2B purchasing app.
Resolved critical issues, optimised SQLs and modularised code blocks which helped in better real time performance of the application.

NLPSQLCode OptimizationNatural Language Processing

Indian institute of technology, bombay

2 roles

M.Tech Project - Numerical Sarcasm Detection

Jan 2017 – Jul 2017 · 6 mos · Mumbai Area, India

Trained traditional ML based classifiers SVM and Random forest on sarcasm based features.
Applied CNN and Bi-directional LSTM networks to compare their performance with the baseline traditional ML models.
Developed an end to end ML pipeline for Numerical Sarcasm detection.
The research was published as a long paper in NAACL-WASSA-2019.

Machine LearningSVMRandom ForestCNNLSTM

M.Tech Project - Sentiment Intensity Ranking of adjectives using Sentiment bearing word embeddings

Jul 2016 – Dec 2016 · 5 mos · Mumbai Area, India

Produced a continuous intensity ranking of adjectives using Neural network based Sentiment bearing word embeddings.
Applied various regression techniques predicting adjective and its intensity.
The research work was presented as conference paper in EMNLP-2017.
The intensity ranking of adjectives can be used for fine-grained sentiment analysis.

Neural NetworksRegression TechniquesNatural Language Processing