Rahul Samant
AI Engineer & Data Scientist
Specializing in AI agent development and LLM applications, I build intelligent systems that solve complex data challenges using Python, LangChain and cutting-edge machine learning.
About Me
Data Scientist & Python Developer
I'm a passionate Data Scientist and Python Developer with expertise in AI-powered automation and advanced web scraping. I design and implement scalable, high-performance solutions to tackle complex data challenges, focusing on cutting-edge machine learning and deep learning methodologies.
Currently pursuing my Bachelor of Technology in Computer Science Engineering at Punjab Engineering College, I've worked on various projects that leverage AI and machine learning to solve real-world problems.
Professional Experience
Generative AI Engineer Intern
Embedded Control Systems
Architected AI-native products using multi-agent workflows, production infrastructure, and automated data extraction to accelerate delivery across cross-functional teams.
Technologies Used
Key Achievements
- Architected intelligent meeting management system using LangGraph multi-agent workflow that automates scheduling, conducts real-time transcription, and generates actionable summaries, reducing meeting overhead by 85% for 5-member team.
- Built production-grade infrastructure on AWS EC2 with MongoDB and FastAPI, serving 3 revenue-generating MVPs with ₹1k MRR and 99.99% uptime.
- Engineered automated Google Maps scraper using LangGraph agents, extracting 50k+ business listings with 95% accuracy and reducing manual research time from 8 hours to 15 minutes.
- Built AI tool recommendation system that suggests productivity tools to non-technical team members based on their workflow patterns, reducing manual task completion time by 45% and improving cross-departmental efficiency.
AI Engineer Intern
Xzayogn (EdTech)
Developed AI-powered job-application automation and search systems to streamline candidate workflows and improve interview conversion rates.
Technologies Used
Key Achievements
- Developed end-to-end job application automation reducing user effort from 6 hours/week to 8 minutes while improving interview rates from 3% to 18%.
- Implemented memory-augmented search with 90%+ relevance filtering across 8 major job boards, eliminating 97% of irrelevant listings.
- Built ATS optimization engine achieving 95%+ ResumeWorded scores through intelligent keyword integration and quantified achievement matching.
- Deployed scalable microservices on AWS Lambda/BeanStalk with TypeScript frontend, serving 50+ beta users.
Python Developer Intern
Infosys Springboard
Built multi-agent scraping and retrieval systems to monitor global e-commerce data and enable fast, natural-language access for analysts.
Technologies Used
Key Achievements
- Engineered Scrapion multi-agent system monitoring 15 global e-commerce sites with 50k+ weekly SKU extraction and RAG-powered enrichment.
- Achieved 5x throughput improvement through async Playwright implementation with hourly data freshness for Fortune-500 retail clients.
- Built natural language query interface using Streamlit and LangChain, delivering sub-second retrieval for business analysts.
Featured Projects
Skills & Expertise
Core Expertise in AI & Data Science
Machine Learning
Advanced algorithms, feature engineering, model optimization
Deep Learning
Neural networks, computer vision, NLP models, transformers
LLM Applications
LangChain, prompt engineering, RAG systems, chain-of-thought
AI Agents & Workflows
LangGraph, autonomous agents, multi-agent systems, agent memory
Technical Skill Set
Python Ecosystem
Expert-level Python programming with specialized data science libraries
AI & ML Frameworks
Building intelligent applications with state-of-the-art AI/ML frameworks
Data Engineering
Complete data pipeline creation from collection to storage and retrieval
DevOps & Cloud
Deploying and scaling ML solutions in production environments
AI Application Focus Areas
NLP & Text Analytics
Sentiment analysis, text classification, document summarization, translation
Conversational AI
Custom chatbots, agent personas, memory management, prompt engineering
Knowledge Management
Retrieval-augmented generation (RAG), semantic search, document query systems
Agent Workflows
Multi-agent systems, autonomous task execution, reasoning agents for complex problems
My Data Science Workflow
1. Data Acquisition
Collection, APIs, scraping
2. Preprocessing
Cleaning, transforming, EDA
3. Modeling
ML/DL models, LLMs, fine-tuning
4. Deployment
APIs, containers, monitoring
Education & Achievements
Education
Punjab Engineering College
Bachelor of Technology in Computer Science Engineering
City Convent School
Senior Secondary Education, CBSE
- Percentage: 95.00%
City Convent School
Secondary Education, CBSE
- Percentage: 90.00%
Achievements & Extra Curricular
- 1
Actively contributed to renowned repositories, including Gradio and Wagtail, enhancing their functionalities and supporting community-driven development.
- 2
Successfully completed Hacktoberfest by having 4 Pull/Merge Requests accepted, demonstrating commitment to collaborative open-source contributions.
- 3
Shortlisted among only 25 candidates for the prestigious Data Science program at IIT Kharagpur, a highly selective achievement in a competitive field.
Skills Development
I continuously focus on improving my technical and soft skills through:
- Online courses and certifications
- Open source contributions
- Hackathons and coding competitions
- Technical workshops and webinars
- Self-learning and practical projects
Professional Resume
My Professional Resume
Here you can view or download my complete resume, which includes detailed information about my skills, experience, education, and achievements.
