Shubham Sarkar — Frontend Engineer

01.

About

I'm Shubham Sarkar, a Frontend Engineer with a strong background in data science and AI. I specialize in creating intuitive web applications that leverage advanced machine learning techniques to enhance user experiences and deliver meaningful results.

02.

Experience

Jan 2026-Present

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.

03.

Selected work

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

Live Demo GitHub

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

GitHub

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

GitHub

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

GitHub

04.

Skills & tools

Machine Learning & AISupervised LearningUnsupervised LearningNatural Language ProcessingComputer VisionLLM Fine TuningRetrieval Augmented GenerationTensorFlowPyTorchscikit-learnHugging FacePandasNumPyLangchainAmazon Web Services (AWS)DockerMLflowDVCFastAPIFlaskStreamlitCI/CDSQLETL PipelinesLinuxVector DatabasesPythonCJavaScriptHTMLCSSData Structures and Algorithms

05.

Education

Jadavpur University

Bachelor of Technology

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

Hariyana Vidya Mandir

High School

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

06.

Leadership & activities

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.

07.

Get in touch

Have a role or a project in mind? I'd love to hear from you.

td19454@gmail.com 0810170328178