ShubhamSarkar
Machine Learning Engineer
@ Alignerr
Transforming complex data into actionable insights through advanced AI and machine learning solutions. 🚀
I’m Shubham Sarkar, a results-driven Machine Learning Engineer passionate about leveraging deep learning, NLP, and computer vision to solve intricate challenges. With a proven track record in enhancing model performance and deploying scalable AI applications, I thrive on driving innovation in the AI landscape.
About Me
I’m Shubham Sarkar, a results-driven Machine Learning Engineer passionate about leveraging deep learning, NLP, and computer vision to solve intricate challenges. With a proven track record in enhancing model performance and deploying scalable AI applications, I thrive on driving innovation in the AI landscape.
CURRENT FOCUS
▹Enhanced LLM evaluation precision by 15% through a comprehensive review of a rubric-based scoring framework across six reasoning categories.
▹Analyzed over 50 audio files for integration into ASR pipelines.
▹Evaluated AI agent responses, identifying failure points such as Inference memory, Self Coherence, and rubric evaluation, resulting in a 20% improvement in model accuracy.
Projects
tailorcv.ai.tsx
01
PYTHON
TailorCV.ai
- Developed an AI web application that optimizes resumes to job descriptions using LLMs and NLP pipelines, improving resume relevance by up to 80%.
- Designed a Python and FastAPI backend with HTML, CSS, and JavaScript for the frontend, dockerized the application, and deployed it on AWS ECS.
- Achieved over 50 users within the first week of launch, demonstrating strong early adoption and real-world impact.
PythonFastAPILLMAI agentsAmazon Web Services
youtube-sentiment-analysis.tsx
02
TENSORFLOW
YouTube Sentiment Analysis
- Created an end-to-end YouTube sentiment analysis pipeline processing over 10,000 user comments, enhancing sentiment classification performance through NLP preprocessing techniques such as tokenization, lemmatization, and stopword removal.
- Tracked multiple model experiments using MLflow and DVC, enabling reproducible training and systematic comparison of models built with scikit-learn and NLP libraries.
- Deployed the pipeline on AWS using Docker and exposed predictions via Flask REST APIs, facilitating scalable and reproducible inference.
TensorFlowNLPAWS EC2Scikit-learn
smart-product-pricing.tsx
03
KERAS
Smart Product Pricing
- Developed 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.
- Built and fine-tuned models using TensorFlow and scikit-learn, achieving a rank of 142 out of 50,000 participants.
KerasHugging Face TransformersResNet50OpenCV
Skills
Languages: SQL
Python
C
JavaScript
HTML
CSS
AI/ML: Machine Learning
Deep Learning
Computer Vision
LLM Fine Tuning
RAG
Frameworks/Libraries: Natural Language Processing (NLP)
TensorFlow
PyTorch
scikit-learn
Hugging Face
Pandas
NumPy
Langchain
Flask
FastAPI
Amazon Web Services (AWS)
Streamlit
ETL Pipelines
Data Structures and Algorithms
Databases: PostgreSQL
Vector Databases (Chroma)
Tools & Platforms: Docker
MLflow
DVC
CI/CD
Linux
Experience
Jan 2026 – Present
Machine Learning Engineer · Alignerr
Remote
- Enhanced LLM evaluation precision by 15% through a comprehensive review of a rubric-based scoring framework across six reasoning categories.
- Analyzed over 50 audio files for integration into ASR pipelines.
- Evaluated AI agent responses, identifying failure points such as Inference memory, Self Coherence, and rubric evaluation, resulting in a 20% improvement in model accuracy.
May 2025 – September 2025
Deep Learning Research Assistant · Jadavpur University CMATER Lab
Kolkata, India
- Designed and implemented a self-attention mechanism (scaled dot-product) within a pre-trained VGG16, significantly enhancing feature extraction for lung cancer detection from CT scans.
- Developed a hybrid deep learning architecture achieving 99.54% peak accuracy with only 76k trainable parameters and 0.0256 GFLOPs, facilitating edge-device deployment.
- Engineered feature fusion through concatenation and element-wise multiplication of original and attention-modulated maps for refined, context-aware representations.
Education
Jadavpur University, Kolkata
Bachelor of Technology
Nov 2023 – Dec 2027 · CGPA: 7.5
Hariyana Vidya Mandir, Kolkata
Higher Secondary
Apr 2020 – Apr 2022 · Percentage: 90%
Leadership
May 2024 – Present
Core Member · Entrepreneurship Cell, Jadavpur University
- Organized national-level events such as E-Summit 2025 and Hult Prize 2025, attracting over 5,000 registrations and 1,000+ attendees.
- Contributed to the establishment of an Incubation Center at Jadavpur University under the Institution’s Innovation Council (IIC).