hello! I'm Sarvesh PV
a tenderfoot in the world of AI & ML.
About Me
Hey there! I'm Sarvesh PV, an AI & ML aficionado on a mission to turn data into impactful solutions. As a problem-solver at heart, I blend deep research, hands-on coding, and leadership to drive real-world innovation.
I'm currently pursuing an M.Sc. in Artificial Intelligence & Machine Learning at the Coimbatore Institute of Technology, where I’ve consistently balanced academic rigor with hands-on innovation maintaining an 8.5 CGPA while exploring real-world applications of AI across diverse domains. My journey is defined by a passion for turning complex challenges into clear, actionable solutions using data and intelligent systems.
Outside the classroom, I’ve taken initiative to shape my community founding student-led platforms, leading innovation-driven teams, and driving peer learning through national-level events and collaborations. Whether mentoring peers or contributing to strategic initiatives, I believe in using technology not just to build, but to empower.
Education
M.Sc. in AI & Machine Learning
Coimbatore Institute of Technology | CGPA: 8.5
High School, Sri Chaitanya School
PCM + Biology | CGPA: 8.7
Professional Experience
ML Engineer Intern, OptiSol Business Solutions
- Building end-to-end production pipelines for client projects
- Implementing automated data validation and model monitoring
HR Manager, The Snippet App
- Led full-cycle recruitment, onboarding 15+ developers & designers
- Streamlined team workflows, boosting productivity by 20%
Leadership & Responsibilities
Board Member, Cyber Security Cell – CIT
Contributed in campus‑wide digital‑safety initiatives on phishing, fraud prevention, and secure coding, impacting the entire college.
Skills: Workshop Design, Security Awareness, Public Speaking, Stakeholder Engagement
Founder & Executive Director, Student Developers Cell – CIT
Established and grew a tech community; organized 30+ hackathons, speaker sessions, and code sprints to foster hands‑on learning in AI/ML, Web Dev, and Cloud.
Skills: Community Building, Event Management, Strategic Planning, Tech Evangelism
Secretary – Google Developer Student Clubs, CIT
Streamlined club operations by coordinating events, managing communications, and liaising with college administration. Ensured seamless execution of guest lectures and collaborative initiatives.
Skills: Operations Management, Stakeholder Coordination, Event Logistics, Internal Communication
Co‑Chairperson, Innovation Vertical – YI YUVA, CIT
Designed and executed innovation challenges and mentorship programs, empowering students to create, innovate and invent and bring in YUVA's vision to the campus.
Skills: Program Design, Mentorship, Cross‑functional Collaboration, Creative Strategy
Head of Innovation – Google Developer Student Clubs, CIT
Led the ideation and delivery of 10+ workshops and internal hackathons on AI/ML and web development. Mentored teams on prototype building, driving a culture of experimentation and technical excellence.
Skills: Innovation Leadership, Technical Mentorship, Workshop Facilitation, Prototype Development
Expertise
Languages & Tools
C, Python, R, HTML/CSS, Git, Docker, Streamlit
Frameworks & Libraries
TensorFlow, Keras, Scikit-learn, Flask, LangChain
Databases & DevOps
MySQL, MongoDB, PL/SQL, REST APIs, CI/CD basics
Publications
"Revolutionizing Genomics with Deep Learning" (ICETST 2025, Coimbatore)
View ProceedingsBlogs & Articles
As a student passionate about Machine Learning and AI, I regularly share my thoughts and learning through articles on Medium. I enjoy translating complex concepts into simple, relatable narratives whether it's AI's cultural limitations or music recommender models. Here are some of my latest pieces:
Why AI Models Might Misinterpret Ancient Proverbs?
This article dives into the challenges Natural Language Processing (NLP) models face when dealing with cultural and metaphorical expressions specifically, ancient proverbs. I discuss why models trained on large corpora often misinterpret figurative phrases due to a lack of context awareness. The piece underscores the significance of domain-specific and culture-aware embeddings, and touches on how linguistic ambiguity poses a serious challenge for current transformer models like BERT and GPT. A must-read if you're working with NLP tasks involving informal or historical text.
Can ML Predict When You'll Get Tired of Your Current Favorite Genre or Artist?
In this piece, I explore the intriguing idea of modeling user boredom and genre fatigue using machine learning. I discuss how platforms like Spotify or YouTube Music might use skip rates, session timing, and listening diversity as behavioral cues to predict when users may shift interests. The article breaks down techniques like RNNs, Transformers, and collaborative filtering approaches used in personalized recommender systems. I also integrate behavioral psychology (e.g., novelty-seeking) to make the idea more relatable. This blog aims to bridge ML algorithms and human emotion a growing edge in modern AI design.
More blogs on model interpretability, GenAI, and real-world ML projects are in the pipeline. Stay tuned!
Projects
Predicting DNA-Protein Binding Motifs
Designed a dual-module deep learning pipeline for motif prediction in genomic sequences. Built a Variational Autoencoder (VAE) for synthetic sequence generation and a CNN-based classifier to predict DNA-protein binding properties. This project supports synthetic biology applications and can accelerate biological discovery through generative learning.
Tech Stack: Python, TensorFlow, Keras, NumPy, Deep Learning
Customer Sentiment Analysis Dashboard
Built a multilingual sentiment analysis dashboard that classifies customer feedback using pre-trained transformer models like DistilBERT and KeyBERT. Added support for real-time text processing using threading, improving inference performance by 30%. Insights are visualized interactively via Streamlit to help brands track sentiment trends across regions.
Tech Stack: Python, Streamlit, Transformers, DistilBERT, KeyBERT, NLP, Matplotlib
SQL Chatbot for Database Interaction
Developed a conversational AI agent that converts natural language to SQL queries. Integrated Groq's LLaMA3 API and enhanced it using prompt-tuning and LangChain agents. The chatbot understands nested logic, aggregates, and filtering queries, streamlining non-technical access to structured data from relational databases.
Tech Stack: Python, LangChain, MySQL, Streamlit, Groq API, Prompt Engineering
License Plate Detection and Recognition
Created a robust ALPR (Automatic License Plate Recognition) system with YOLOv8 for vehicle plate detection and Tesseract OCR for real-time character recognition. Trained on a custom-annotated dataset with bounding box annotations. Supports multilingual plates and is deployable as a lightweight Streamlit app.
Tech Stack: YOLOv8, OpenCV, PyTorch, Tesseract OCR, Python, Streamlit
Cross-Platform Meal Planner
Designed a user-centric mobile app that helps users plan meals using location, preferences, and dietary goals. Implements RSS-based food blog updates, email auth, and offline SQLite session tracking. Provides smart grocery suggestions and calorie summaries for each meal plan turning food habits into data-driven decisions.
Tech Stack: Flutter, Dart, SQLite, REST APIs, Riverpod, Email Auth, RSS Feeds
Resume
Let's Connect
I'd love to hear from you! Whether it's a project idea, mentorship opportunity, or networking interest feel free to reach out through any of the channels below:
GitHub
github.com/sarrvesshPortfolio
linktr.ee/sarrvesshResume
Download Resume (PDF)Location
Coimbatore, Tamil Nadu, India
Whether it's a question, collaboration, freelance opportunity, or just a hello...I'd be thrilled to connect with you.