Summary
Overview
Education
Skills
Certification
Timeline
Work History
projects
projects
Hi, I’m

Kunal Biswas

AIML ENGINEER
Delhi-NCR
Kunal Biswas

Summary

Transforming Data into Intelligence with Python-Powered AI/ML Solutions. Leveraging advanced algorithms and deep learning techniques to drive innovation and optimize performance. Proven expertise in developing scalable, efficient machine learning models and deploying them in production environments. Dedicated to enhancing data-driven decision-making and delivering impactful results.

Overview

4
years of professional experience
6
years of post-secondary education
2
Certificates

Education

IIT Jodhpur
Jodhpur, Rajasthan

Post-Graduation Diploma Masters of Technology from School of Artificial Intelligence And Data Science
09.2023 - 06.2025

University Overview

Product Review Analysis (Trimester 1 Project)

  • Developed multiple applications, including Sentiment Analysis on customer reviews.
  • Implemented a suggestion system to improve products by distinguishing constructive criticism from non-constructive feedback.
  • Created an inventory stacking system based on sales data and customer feedback, tailored to region and season.

Fake News Campaign Detection (Trimester 2 Project) for Social Network Analysis

  • Utilized Graph Neural Networks (GNN) to detect the spread of fake news and assess the impact of specific networks in disseminating misinformation.
  • Implemented Bidirectional LSTM for keyword detection to identify fake news, contributing to a research paper.
  • Graduation with Distinction,

3D indoor map generator using Advance Computers Vision

  • Tech Stack: Node.js, OpenCV, WebSockets, Express.js, Three.js, QR Code Scanning, REST API
  • Developed a 3D indoor navigation system leveraging advanced computer vision and Node.js to generate dynamic route maps for large complexes such as hospitals, malls, and universities.
  • Implemented real-time indoor mapping using OpenCV and Three.js to visualize paths in 3D.
  • Enabled users to scan a QR code at entry points to connect to the server and retrieve their current location.
  • Designed a location-based routing algorithm to compute and display the optimal path to the selected destination.
  • Built a backend with Express.js and WebSockets for live updates and smooth navigation assistance.
  • Ensured scalability and cross-platform support for integration in multi-building infrastructures.

Custom Annotation Tool & Automated Model Trainer for YOLO/ONNX Models For Advance Computer Vision

  • Tech Stack: Python, OpenCV, Flask, HTML/CSS, JavaScript, LabelImg, YOLOv5/YOLOv8, ONNX, Reinforcement Learning, NumPy, Pandas
  • Developed a custom annotation and model training pipeline to streamline dataset preparation and training for advanced computer vision models.
  • Built a lightweight annotation tool inspired by Roboflow and LabelImg with a user-friendly HTML interface to upload videos, extract frames (FPS-based), and define dataset split ratios (train/val/test).
  • Integrated automated frame extraction using OpenCV and handled dataset organization dynamically through the backend.
  • Implemented reinforcement learning-based annotation assistance to reduce manual effort and improve label accuracy.
  • Enabled seamless YOLOv5/YOLOv8 and ONNX model training post-annotation, with automated hyperparameter tuning and output of optimized `best.pt` or `best.onnx` model files.
  • Designed the entire workflow to support rapid prototyping and deployment of custom object detection models for various use cases.

Stock market fluctuations analysis based on Stock news for Financial Analysis

  • Tech Stack: Python, BeautifulSoup, Requests, Pandas, NLTK/VADER, Matplotlib, Yahoo Finance API, Groww Web Scraping, Jupyter Notebook
  • Conducted financial analysis by correlating stock price fluctuations with sentiment analysis of stock-related news.
  • Built a data pipeline to scrape stock price data from Yahoo Finance and related news from the Groww website, based on stock ticker and date range.
  • Combined 7-day historical stock metrics (open, close, volume, etc.) with corresponding news headlines to create a unified dataset.
  • Performed sentiment analysis using NLTK/VADER to quantify the emotional tone of news articles and assess their impact on stock performance.
  • Automated data collection for a one-month period to identify patterns and correlations between news sentiment and market movement.
  • Visualized findings through insightful plots and trends to support financial reporting and decision-making.

Audio translation with voice cloning for Speech Understanding

  • Tech Stack: Python, FFmpeg, OpenAI Whisper, Coqui TTS, PyDub, IndicTrans2, Hugging Face Transformers
  • Built a complete speech-to-speech pipeline to enable multilingual accessibility of classroom lectures with realistic voice cloning, especially for Indian languages.
  • Extracted high-quality audio from a 2-hour classroom video using FFmpeg.
  • Transcribed and detected source language using OpenAI Whisper for accurate speech-to-text conversion.
  • Translated transcribed text into Indian languages (e.g., Hindi, Bengali, Tamil) using IndicTrans2 and Hugging Face Transformer models.
  • Synthesized translated speech using Coqui TTS with speaker voice cloning for a natural and consistent audio output.
  • Processed and merged audio segments using PyDub for clean and continuous playback.
  • Designed for long-form content, with use cases in education, accessibility, and e-learning platforms.

Speech and Noise Separation with Classification for Forensic Audio Analysis for speech understanding

  • Tech Stack: Python, Demucs, Spleeter, Noisereduce, Librosa, OpenSMILE, scikit-learn, PyTorch
  • Built an advanced audio processing pipeline for forensic analysis by separating speech from multiple background noises and classifying environmental sounds.
  • Leveraged Demucs and Spleeter for high-fidelity speech and noise separation in overlapping audio scenarios.
  • Integrated Noisereduce and Librosa for noise suppression, feature extraction, and signal enhancement.
  • Developed a noise classification module using OpenSMILE for feature extraction and scikit-learn for sound category prediction (e.g., crowd, vehicle, music).
  • Implemented a demasking algorithm to reconstruct masked or distorted speech segments, improving clarity and speaker intelligibility.
  • Designed for use in forensic environments, enabling investigators to extract usable speech and noise insights from complex audio evidence.

RAG-based Legal Document Intelligence System with Graph & Vector Databases

  • Tech Stack: Python, LangChain, ChromaDB, Neo4j (Community Edition), Hugging Face Transformers, LLaMA 3 (8B via Groq), BEIR, SentenceTransformers, PyPDF2, NetworkX, Streamlit
  • Designed and deployed a Retrieval-Augmented Generation (RAG) system to streamline legal research by enabling intelligent querying within and across legal documents.
  • Deployed LLaMA 3 (8B) on Groq for low-latency, high-performance response generation integrated into the RAG pipeline.
  • Trained a SentenceTransformer model using the BEIR benchmark dataset to enhance general-purpose semantic search capabilities.
  • Replaced FAISS with ChromaDB, an open-source vector database, for managing dense document embeddings and efficient retrieval.
  • Built graph representations of legal documents using Neo4j and NetworkX, enabling inter-document citation tracking and intra-document clause linking.
  • Utilized Hugging Face Transformers (e.g., Legal-BERT) for embedding generation and legal language understanding.
  • Extracted and structured text from court judgments and legal PDFs using PyPDF2.
  • Developed a user-friendly Streamlit interface where legal professionals can query by natural language and receive targeted, explainable summaries and references.
  • Significantly reduced time and cognitive effort in searching legal precedents and analyzing multi-case dependencies.

SRM Institute of Science And Technology
Delhi-NCR Campus

Bachelor of Technology from Computer Science And Engineering
07.2016 - 07.2020

University Overview

  • Developed facial and retinal recognition systems using Haarcascade and OpenCV with device cameras.
  • Implemented Optical Character Recognition (OCR) for converting handwriting and PDF documents to Word files using Python and Pytesseract.
  • Created Text-to-Speech and Speech-to-Text applications for voice-based Google searches utilizing the gTTS (Google Text-to-Speech) module.
  • Executed a machine learning project on environmental noise recognition for potential noise cancellation applications, using Python and the Librosa module for sound data analysis.
  • Built basic games using Unity 3D and designed objects with Blender.

Skills

SQL

Certification

NLP(ude.my/UC-1a54c6ac-44df-4fb7-a1b1-8ed5d541fde4)

Timeline

Consultant (AIML Engineer)

Audax Labs
01.2025 - Current

AIML Engineer

Walking Tree Technologies
12.2023 - 01.2025

IIT Jodhpur

Post-Graduation Diploma Masters of Technology from School of Artificial Intelligence And Data Science
09.2023 - 06.2025

NLP(ude.my/UC-1a54c6ac-44df-4fb7-a1b1-8ed5d541fde4)

03-2022

Deep Learning A-Z(ude.my/UC-6c9d0dd4-dff0-4bfc-b4fc-5c4f512e5a62)

11-2021

Machine Learning Engineer

Cognizant Technology Solutions
09.2021 - 07.2023

SRM Institute of Science And Technology

Bachelor of Technology from Computer Science And Engineering
07.2016 - 07.2020

DBA

Cognizant Technology Solutions
9 2020 - 9 2021

Work History

Audax Labs
Noida, Uttar Pradesh

Consultant (AIML Engineer)
01.2025 - Current

Job overview

  • Contributed to Data Beagle, a data privacy product, by developing core features for detecting sensitive information such as SSNs, PII, and PHI, and building dynamic Solr query generators to improve search and compliance automation.
  • Designed and implemented a log analysis POC using an Agentic approach, classifying log types, categorizing them, and triggering actions like Jira ticket creation, email alerts, or Slack notifications based on predefined scenarios.
  • Developed and integrated a pause and resume mechanism for a distributed large-scale data migration tool, improving reliability and control over long-running jobs.
  • Built a school bus safety system using computer vision for monitoring child activity and safety compliance, deployed on NVIDIA Jetson for real-time, on-premise inference in school buses across the USA.

Walking Tree Technologies
Noida

AIML Engineer
12.2023 - 01.2025

Job overview

  • Demonstrated strong team management and coordination skills, effectively leading cross-functional teams to achieve project milestones.
  • Proactively identified and resolved critical issues during Document ingestion phases, ensuring seamless transitions between design iterations.
  • Spearheaded R&D initiatives to explore cutting-edge AI/ML techniques, driving continuous innovation
  • Developed and implemented document parsers for various formats, including DOCX, Excel, Text, PDF, and Scanned PDF.
  • Utilized RAG, Stuff Chain, LangChain LLM, and AutoGen Multi-Agent LLM for advanced document processing.
  • Leveraged OCR and computer vision techniques for efficient image processing.

Cognizant Technology Solutions
Chennai

Machine Learning Engineer
09.2021 - 07.2023

Job overview

  • Healthcare AI/ML Engineer with Expertise in Python and Deep Learning
    Project: Health Insurance Plan Prediction

    - Developed a deep learning model (ANN) to predict most suitable health insurance plans based on customer requirements, enhancing brokers' ability to sell plans effectively.
    - Utilized parameters such as budget, medical history, specific diseases, age, and disability to tailor recommendations.
    - Analyzed a variety of Medicare, Medicaid, and general health insurance policies to find optimal match for customers.
    - Leveraged data visualization to gain insights that drive creation of new plans and optimization of existing ones, catering to regional preferences and identifying top-performing brokers.

    Project: Pharmacy Business Management (PBM) - Optimal Drug Inventory Stacking [Prototype]

    - Designed and implemented a deep learning model (ANN) to predict optimal amount of medicines for inventory, preventing shortages and overstock situations, thereby maximizing profit for PBM industries.
    - Completed an end-to-end project utilizing Flask to create an API for model deployment and developed a web application for user interaction.
    - Deployed solution using Amazon EC2 services for robust and scalable hosting.

Cognizant Technology Solutions
Chennai

DBA
9 2020 - 9 2021

Job overview

  • Crafted and executed SQL queries tailored to client specifications, improving data retrieval efficiency by 30%.
  • Maintained comprehensive documentation of program development and revisions, ensuring clear project tracking and knowledge transfer.
  • Swiftly addressed and resolved critical issues, reducing system downtime by 20%.
  • Managed, maintained, and secured data across multiple systems, enabling team to conduct business analyses with 99% data accuracy.
  • Evaluated customer requirements and optimized existing databases, enhancing performance and meeting client specifications, resulting in 20% increase in database query speed.

projects

  • Medical Aid Reimbursement(Fraud Detection Analysis)

As per my project in current company is related to healthcare in which an deep learning model(ANN) is used to predict whether patient is eligible for medicare or medicaid and if medicaid upto what extent.

  • Hate Speech Detection(for learning purpose)

I have used twitter dataset from kaggle using NLP(NLTK and Spacy) for preprocessing(TF-IDF for word vectorization) the data. Then used Deep Learning Model (RNN)

  • Environmental sound detection( For learning purpose)

Used python Package LIBEROSA for feature extraction of audio dataset and used Machine Learning model(Random Forest) using ML framework from Scikit Learn

  • Stock Market Prediction(Predictive Analysis)

Used deep learning model(ANN) using DL framework tensorflow and keras.

  • Cat and Dog Classification( For learning purpose)

Using both keras.preprocessing.image(with CNN) and skimage(with SVM)

  • Speech to Text and Text to Speech(For learning Purpose)

Using Google Text to Speech(gTTS)

projects

  • Medical Aid Reimbursement (Fraud Detection Analysis)In my current role, I developed a deep learning model (ANN) to predict patient eligibility for Medicare or Medicaid and determine the extent of Medicaid coverage. This project focuses on fraud detection in the healthcare sector.
  • Hate Speech Detection (Learning Project)Utilized a Twitter dataset from Kaggle, leveraging NLP techniques (NLTK and SpaCy) for preprocessing and TF-IDF for word vectorization. Implemented a Deep Learning model (RNN) to detect hate speech.
  • Environmental Sound Detection (Learning Project)Employed the LIBROSA package for feature extraction from audio datasets and developed a Machine Learning model (Random Forest) using Scikit-Learn for environmental sound classification.
  • Stock Market Prediction (Predictive Analysis)Built and deployed a deep learning model (ANN) using TensorFlow and Keras to predict stock market trends and inform trading strategies.
  • Cat and Dog Classification (Learning Project)Developed image classification models using both Keras (with CNN) and Scikit-Image (with SVM) to distinguish between cat and dog images.
  • Speech to Text and Text to Speech (Learning Project)Implemented Google Text-to-Speech (gTTS) for converting speech to text and vice versa, enhancing user accessibility and interaction
Kunal BiswasAIML ENGINEER