Creating robust AI-driven solutions that enhance data processing and decision-making.
I'm Susan Garcia, a passionate Backend Engineer specializing in AI and machine learning. With a solid foundation in deploying end-to-end software solutions, I thrive on transforming complex data into actionable insights that drive innovation and efficiency.
Machine Learning & AI
Supervised Learning
Unsupervised Learning
Natural Language Processing
Computer Vision
LLM Fine Tuning
Retrieval Augmented Generation
TensorFlow
PyTorch
scikit-learn
Hugging Face
Pandas
NumPy
Langchain
Amazon Web Services (AWS)
Docker
MLflow
DVC
FastAPI
Flask
Streamlit
CI/CD
SQL
ETL Pipelines
Linux
Vector Databases
Python
C
JavaScript
HTML
CSS
Data Structures and Algorithms
Developed an AI web application that customizes resumes to align with job descriptions, enhancing resume relevance by up to 80%. Engineered a Python and FastAPI backend, complemented by HTML, CSS, and JavaScript for the frontend, deployed on AWS. Achieved over 50 users within the first week of launch, demonstrating strong early adoption and real-world impact.
Created a comprehensive YouTube sentiment analysis pipeline processing over 10,000 user comments, enhancing sentiment classification performance through advanced NLP preprocessing techniques. Tracked multiple model experiments using MLflow and DVC, facilitating reproducible training and systematic comparison of models developed with scikit-learn and NLP libraries. Deployed the pipeline on AWS utilizing Docker, exposing predictions via Flask REST APIs for scalable and reproducible inference.
Developed a production-ready RAG pipeline integrating semantic vector retrieval with LLM generation to produce context-grounded responses. Engineered multiple chunking strategies and a scalable ingestion, retrieval, and generation flow for efficient semantic search and generation. Implemented history-aware and multimodal augmentations, evaluating retrieval outputs to measure relevance and quality.
Created an NLP and CV pipeline to analyze 150,000 image and text data using transformer-based text encoders and CNN-based image embeddings, integrating them through a fusion neural network for price prediction. Implemented data preprocessing techniques, including text cleaning, tokenization, and streaming image feature extraction with ResNet and CLIP representations to manage large datasets. Applied feature engineering, outlier handling, and SMAPE-based evaluation to optimize prediction accuracy, achieving a rank of 142 out of 50,000 participants.
Organized national-level flagship events such as E-Summit 2025 and Hult Prize 2025, achieving over 5,000 registrations and 1,000+ on-campus attendees. Contributed to the establishment of an Incubation Center at Jadavpur University under the Institution’s Innovation Council (IIC).
Led planning and execution of Finspire 2025, a national-level finance event with over 1,000 registrations and 500+ on-ground attendees, strengthening the club’s national presence. Delivered high-impact trading and investment courses to over 100 students, enhancing engagement in financial markets.
Have a role, project, or collaboration in mind?