Data Scientist

About Me!

👋 Hi there! I’m a Data Scientist with a passion for Machine Learning, Deep Learning and Data Science. With two years of experience in technical sales, I’ve had the opportunity to bridge the gap between business needs and cutting-edge ML solutions. My focus is on implementing practical machine learning solutions that address real-world challenges. Let’s build something great together!

Skills

Languages: Python, SQL, Java
Python Frameworks and Packages: Tensorflow, Keras, Langchain, MLflow, Scikit-learn, Numpy, Pandas
Cloud Platforms: GCP, AWS
Tools: Docker, SQL Workbench, Tableau, PowerBI, Neo4J
Domain Expertise: Classical ML, Computer Vision, NLP, Sequence-to-Sequence models, Transformers, RAG, Data Analysis and visualization

Work Experience

Machine Learning Engineer @ Quantiphi Analytics Solutions Private Limited (August 2024 - Present)

Deployed an end to end Deep Learning project on AWS using AWS EC2, ECR, Elastic BeanStalk, Docker for containerization and integrated CI/CD pipelines using GitHub Actions along with MLFlow for model experimentation, versioning and tracking as a part of a 12 week training program under the mentorship of a data scientist
Created Retrieval-Augmented Generation (RAG) systems for conversational agents that interact with data from user uploaded PDFs and websites using the LangChain frameowrk, OpenAI and HuggingFace embeddings and models, ChromaDB and FAISS as vector databases and Streamlit Cloud for deployment
Covered classical Machine Learning, Deep Learning, Computer Vision, Natural Language Processing, Sequence-to-sequence models during the training program

Business Analyst | Custom ML Solutions @ Quantiphi Analytics Solutions Private Limited (August 2022 - August 2024)

Responsible for understanding, analyzing and solving complex problems through AI across a variety of industries including BFSI, Energy and Retail & CPG
Collaborated with client stakeholders to ensure business and technology alignment through meetings, workshops, and workflow analysis
Proposed solutions meeting defined specifications and needs with alignment from client and internal development teams
Developed business solution flows and technical architectures basis client requirements and translated requirements into tangible deliverables
Handled leads from 5 different regions globally, namely US East, Canada, EMEA, APAC, and India
Successfully took ownership and assisted in closing engagements with a total deal value of over $1M

Business Consulting Intern | Performance Improvement @ Ernst & Young LLP (December 2021 - July 2022)

Extracted and transformed data from client databases to build dashboards in Power BI which tracked inventory levels of over 2,000 suppliers and 43,000 parts
Developed a dashboard in PowerBI to identify production bottlenecks in the supply chain
Worked on SQL query optimization to decrease execution time by over 30%
Identified Key Performance Indicators and developed storyboards to assess the client’s situation and assist in informed decision making
Facilitated the implementation of a Graph DB solution using Neo 4j

Projects

Chat with your PDFs via RAG

Developed a RAG-based application using OpenAI models and Instructor Embeddings from Hugging Face, leveraging Faiss for storing PDF embeddings, allowing users to query multiple uploaded PDFs via natural language, deployed on Streamlit Cloud.

Chat with any website via RAG

Developed a RAG-based application using OpenAI models and embeddings, with ChromaDB for storing website embeddings, enabling users to interact with websites via natural language queries, deployed on Streamlit Cloud.

Brain Tumor Classification from MRI Scans using CNN

Deployed an end to end Deep Learning project on AWS using AWS EC2, ECR, Elastic BeanStalk, Docker for containerization and integrated CI/CD pipelines using GitHub Actions along with MLFlow for model experimentation, versioning and tracking

Segmentation of Cars from images using UNET

Trained a UNET model for image segmentation to detect and extract cars from horizontal and vertical orientations using 20 annotated images with image masks

Education

M.Sc., Big Data Analytics St. Xavier’s College, Mumbai (August 2022)
B.SC., Information Technology St. Xavier’s College, Mumbai (August 2020)

Joshua Miranda