Apoorv Agarwal

Experience

• 

  Blackcoffer

  Nov 2017 - Apr 2018

  Research Analyst

  Involves working on a variety of projects like market research and analysis or working on research problems solved with the aid of Data Analytical tools and programming languages like R and python.

• 

  Mercedes-Benz Research and Development India

  Dec 2018 - Jun 2019

  Data Scientist

  Advanced Energy Management and Battery Range Extension:-Predictive Study of Energy demand for E-Citaro buses going over some route, on the basis of several parameters which affects the traction and Auxiliary Energy requirement. Also, to design a controller to extend Battery range and also optimize the Charging Schedule for efficient fleet management.

• 

  RBG Labs, IIT Madras

  Jul 2019 - May 2020

  Student Researcher

  Thesis title: - DATA PRE-PROCESSING AND PREDICTIVE MODELLING FOR ROAD ACCIDENT SEVERITY PREDICTIONDescription: Road Safety, under the guidance of Dr Venkatesh Balasubramanian, Engineering design Department. The project involves predicting the road accident severity and identifying the major factors on Chennai Road Accident database (RADMS database). The project involves exploring and implementing various techniques to identify and handle Data biases and imbalances and implementing data encoding techniques to train the Machine Learning model. Exploring various Machine Learning models for achieving high accuracy results and extending its usability. Implementation of Cross-validation techniques and Data Visualization for better understanding of results. Tools used:- Python, R, ADASYN, K-fold cross-validation, k-NN, SMOTE, DTC Show less

• 

  VMock

  Dec 2020 - May 2021

  Data Scientist

  **TRAINING PERIOD**1. Revised key concepts of classical machine learning (Regression Analysis, Decision Trees, Random Forests, Naive Bayes, Artificial Neural Network)2. Learnt the fundamental concepts of NLP and text analytics (Word2Vec models, Skipgrams and CBOW models, Negative sampling, Topic Modelling, Latent Dirichlet Allocation model, Ngrams)3. Worked on important Deep Learning concepts (CNNs, RNNs, LSTMs, speech recognition, Video analytics, Image processing)4. Learnt basic concepts of Python web development ( Flask, uWSGI, JWT authentication, supervisor, apache proxy pass, celery, TensorFlow-serving. Also, developed an API for uploading, updating user input CSV data and secured the routes with proper user-based authentication)**PROJECT**Section Mapping:-1. Implemented Topic Modelling to segregate Resume text data into various sections for the Resume Parser.2. Created a Labelled Latent Dirichlet Allocation model for developing Topic-Word distribution and Word-Document distribution matrices.3. Improved baseline model, which used Continous Bag Of Words method, with Ngrams implementation (Bi-grams and Tri-grams).4. Added Spacy noun chunks, adjectives and verb tokens to further refine the model accuracy.5. Conducted error analysis for creating appropriate section buckets by optimizing the Confusion matrixTools used: NLTK, regex, Spacy, Tomotopy, k-Folds, Python, Excel. Show less

• 

  Oriserve

  Jun 2021 - now

  Email Bot(Vodafone): Implemented RoBERTA architecture for fine-tuning and context comprehension. Improved bot handling percentage by +30%Voicegenie.ai: Spearheaded the development of Voicegenie(Website: https://voicegenie.ai/), a groundbreaking Voice AI solution renowned for its generative capabilities. My involvement spanned from audio processing and optimization library integration to architecting the complex speech generation framework that underpins Voicegenie's success.Voicegenie UseCase Development: 1) Lead collection strategies for Pristyn-Care 2) Flight rescheduling solutions for Air India3) Vodafone retention Bot4) Debt Collection for L&T Financial Services5) JARVIS Survey collection bot6) Bajaj Allianz Life Insurance Outbound Voicebot7) Tradejini Inbound VoicebotR&D: 1) Implementation of in-house generative models such as LLAMA, MPT, FALCON etc. at scale2) Real-time voice cloning and Transliterated speech generation3) Emotion-based Text-to-Speech model4) In-flight batching implementation of LLMs for reducing latency and improving concurrency5) Dynamic On-loading and Off-loading of CUDA models for efficient Memory Management and server cost reduction6) Finetuning(full weights and PEFT) implementation of various DL model currently used for better maintenance of ML production lifecycle Show less ORI is an end-to-end provider of conversational AI-powered chatbots, with the sole intention of helping enterprises make the customer experience count. Ori is focused on automating the customer journey which it does through its connected, multilingual, omnichannel, self-service platform, made by applying design thinking principles and AI.Our cognitive AI solutions provide a non-intrusive customer experience for Sales, Marketing, Support & Engagement across IoT devices, sensors, web, app, social media & messaging platforms. Our Products:1. Chatbot: Voice + Text Compatible, Hybrid (Live + AI), Multiple Context Switching, Omni-channel along with Recovery Based Mechanisms.2. Email Based Responder Bots: Automate Email Support with Resolutions Handed Without Manual Intervention.3. Customer Service Agent Support Bots: Assist Agents with Prompts & Queues During Customer Conversations Over Chat + Calls.4. Voicebot: Fully speech-based end-to-end AI voice assistant with ASR capabilites (transcription and translation, language detection, accent handling), along with realtime Text-to-Speech response back to the user, supported through both Web and cloud telephony interface. Show less

  • Lead Data Scientist

    Jun 2024 - now

  • Senior Data Scientist

    Jun 2023 - Jun 2024

  • Data Scientist

    Jun 2021 - Jun 2023
• 

  Topmate.io

  Jul 2024 - now

  Data Science Career Mentor

  I just want to do my part for the amazing, growing AI community. With the democratizing of myriads of AI technologies, concepts, and algorithms, it is overwhelming to decide what and where to focus when starting your career or maybe progressing to a better role in AI. I believe that I can help you in finding and "fine-tuning" some key aspects that will be useful to you for nurturing or starting a great career in Data Science. So what are you waiting for? Let's talk!