> INITIALIZING PORTFOLIO...
Hello,
I'm |
Data Scientist & ML Engineer
🎓 MS in Data Science | 💻 ML & AI Enthusiast | 🧠 Lifelong Learner
class DataScientist:def __init__(self):self.name = "Aditya Malkar"self.skills = ["Python", "PyTorch","TensorFlow","AWS", "Spark", "LangChain"]self.passion = "Building AI Solutions"def is_hireable(self):return True # Always!> WHO_I_AM
Turning Data into Insights
I'm Aditya Malkar, a Master's student in Data Science passionate about building impactful projects in machine learning, AI, and data analytics. My journey in technology is fueled by curiosity and a relentless drive to make data meaningful. I specialize in developing deep learning models, building AI-powered solutions, and analyzing complex datasets for actionable insights. From Speech-to-Speech translation systems to Diabetic Retinopathy classification, I love tackling challenging problems with innovative approaches. I'm proficient in Python, PyTorch, TensorFlow, AWS, and various data tools. Always eager to collaborate on AI-powered solutions and open-source projects!
Machine Learning Intern - Image Classification
Prodigy Infotech, Mumbai, India
Machine Learning Intern - Model Optimization
TechnoHacks Edutech, Nashik, India
Data Science Projects
Independent Research & Development
Also proficient in: R, SQL, PySpark, Pandas, Scikit-learn, Keras, LangChain, Streamlit, MediaPipe
Real-Time Speech-to-Speech Translation
classProject:name= "Real-Time Speech-to-Speech Translation"tools = ["Python", "PyTorch", "Whisper", "MarianMT", "Meta MMS-TTS", "Silero VAD", "Threading"]role= "ML Engineer"# Description"""Architected a low-latency, concurrent translation pipeline using producer-consumer model with Python threading, achieving ~2.8s pipeline depth. Integrated Whisper Medium for STT (4% WER) and MarianMT for translation, achieving BLEU scores of 80.85 (EN→ES) and 71.64 (EN→FR). Implemented custom VAD using Silero with <3ms frame latency and engineered hallucination filters."""Diabetic Retinopathy Classification
classProject:name= "Diabetic Retinopathy Classification"tools = ["Python", "Apache Spark", "Azure Blob Storage", "TensorFlow", "VGG-16", "TFRecords", "Deep Learning"]role= "Data Scientist"# Description"""Processed a large-scale image dataset (143,509 images, ~22GB) using Apache Spark with Azure Blob Storage for distributed access. Engineered a deep learning pipeline using custom VGG-16-based CNN, achieving 87%+ accuracy in identifying diabetic retinopathy severity levels. Reduced training time by 40% using Spark distributed compute."""AI-Powered Career Advisor
classProject:name= "AI-Powered Career Advisor"tools = ["LangChain", "AWS Bedrock", "Claude V2", "Streamlit", "RAG", "Python", "Agentic AI"]role= "AI Engineer"# Description"""Architected an autonomous chatbot using LangChain, AWS Bedrock (Claude V2), and Streamlit with Agentic AI concepts like goal-seeking and tool-use. Developed a RAG pipeline that increased response relevance by 40% by integrating external career data. Designed an alignment & safety framework that reduced model hallucinations by 75%."""MultiModal Twitter Sentiment Analysis
classProject:name= "MultiModal Twitter Sentiment Analysis"tools = ["Python", "Keras", "TensorFlow", "LSTM", "BERT", "NLP", "Deep Learning"]role= "ML Engineer"# Description"""Preprocessed 1.6 million tweets using tokenization, stopword removal, and stemming. Implemented deep learning pipeline using Sequential Model with Embedding, Conv1D, MaxPooling1D, and LSTM layers, achieving 85%+ accuracy. Compared SVM, Decision Tree, Bi-LSTM, and BART models, achieving 12-18% higher F1-score with deep learning approaches."""AI Agent for Automated Credentialing
classProject:name= "AI Agent for Automated Credentialing"tools = ["AWS (RDS, EC2)", "LangChain", "React", "Node.js", "Python", "OpenAI API"]role= "Full Stack AI Developer"# Description"""Developed CrediSync, a multi-agent automation system for hospital credentialing, reducing manual form-filling time by ~90%. Engineered dual-agent architecture with LangChain: Parser Agent extracted 15+ key entities from PDFs, Form Filler Agent achieved 100% field mapping accuracy. Built custom Chrome extension for one-click auto-filling."""Neural Image Compressor
classProject:name= "Neural Image Compressor"tools = ["Python", "PyTorch", "Deep Learning", "Computer Vision", "AWS"]role= "ML Researcher"# Description"""Working on Neural Data Compression for Images and Videos, exploring state-of-the-art deep learning techniques for efficient media compression while maintaining quality. Building foundation in AWS cloud services for scalable deployment."""Master of Science in Data Science
Stevens Institute of Technology
Bachelor's Degree
University of Mumbai