Hi, I am uttam debnath
Backend Engineer 

Crafting robust backend solutions that drive AI-powered applications and enhance data-driven decision-making.

Get in touch

About Me

I am Uttam Debnath, a Backend Engineer with a passion for developing end-to-end software solutions. My expertise lies in leveraging machine learning and AI to transform unstructured data into actionable insights. I thrive on creating efficient systems that deliver real-world impact.

Skills

TensorFlowPyTorchAmazon Web Services (AWS)DockerFastAPIFlaskLinuxPythonCJavaScriptHTMLCSSData Structures and Algorithms Machine Learning & AISupervised LearningUnsupervised LearningNatural Language ProcessingComputer VisionLLM Fine TuningRetrieval Augmented Generationscikit-learnHugging FacePandasNumPyLangchainMLflowDVCStreamlitCI/CDSQLETL PipelinesVector Databases

Experience

Machine Learning Engineer

Alignerr

  • Enhanced model prediction accuracy by 15% through comprehensive analysis of agent responses across various rubrics and state scenarios.
  • Transcribed over 50 audio and video files to generate high-quality training and test datasets.
  • Evaluated LLM conversations to assess the correctness of tool usage, API calls, and reasoning flow.
Jan 2026-Present

Featured Projects

Tailorcv.ai

Tailorcv.aiCheck out ↗

AI web app utilizing LLMs and NLP pipelines

  • 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.
AI web app utilizing LLMs and NLP pipelines
Youtube Sentiment Analysis

Youtube Sentiment AnalysisCheck out ↗

End-to-end sentiment analysis pipeline

  • 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.
End-to-end sentiment analysis pipeline
RAG System

RAG SystemCheck out ↗

Production-ready RAG pipeline

  • 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.
Production-ready RAG pipeline
Smart Product Pricing Model, Amazon ML Challenge 2025

Smart Product Pricing Model, Amazon ML Challenge 2025Check out ↗

NLP and CV pipeline for price prediction

  • 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.
NLP and CV pipeline for price prediction

Education

Bachelor of Technology

Jadavpur University

2023-2027 · Secured 98.5 percentile in JEE Mains out of 1,400,000 students and 1458 rank in WBJEE

High School

Hariyana Vidya Mandir

2020-2022 · Scored 96% in class 10 and 92% in class 12

Activities & Leadership

Core Member @ Jadavpur University Entrepreneurship Cell

  • 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).

Coordinator @ Jadavpur University Finance Club

  • 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.

Get In Touch

Have a role or a project in mind? Let's build something together.

Say hello ✉️