I architect scalable software, orchestrate agentic systems, and ship workflows that deliver real-world value.

Sarvesh PV · AI/ML Engineer

Agentic Workflows Resilient Backends Production AI on Cloud

Production-first engineering across cloud ML, autonomous workflows, and resilient backend systems.

About / Build DNA

Founder. Technocrat. Wordsmith. Mentor.

I build software where AI is part of the operating layer, not a bolt-on feature. That means autonomous workflows, dependable APIs, and backend systems designed for messy real-world traffic.

I am currently pursuing an M.Sc. in Artificial Intelligence & Machine Learning at Coimbatore Institute of Technology, while spending most of my time building and shipping. In industry work, I have built FastAPI services, AWS data and ML pipelines, and risk modeling flows that moved from experiments into daily operations.

I naturally gravitate to high-scale backend challenges where latency budgets, failure behavior, and cloud cost are first-class design inputs. Outside build cycles, I show up at AI events and hackathons to pressure test ideas, sharpen execution, and meet people serious about building durable AI products.

5+ projects shipped, 2 Medium articles, 1 conference publication, and 4 leadership roles.

Education

2022 - Present

M.Sc. in AI & Machine Learning

Coimbatore Institute of Technology | CGPA: 8.5

2019 - 2022

High School, Sri Chaitanya School

PCM + Biology | CGPA: 8.7

Professional Experience

ML Engineer Intern

Jun 2025 - Nov 2025

OptiSol Business Solutions

Engineered a scalable backend and cloud data pipeline using FastAPI and AWS to automate telematics ingestion across 9+ provider ecosystems.
Architected a hybrid ensemble risk model (LightGBM + CatBoost) with SMOTE for imbalanced crash-event data, achieving strong classification performance in production testing.
Built and validated model workflows on AWS SageMaker and accelerated telematics feature engineering and exploratory analysis using AWS Glue.
Developed a full-stack React operations control panel with embedded Power BI dashboards and role-based access control (RBAC) user paths.
Instituted end-to-end validation across frontend flows, API contracts, and cloud deployment paths, cutting review overhead and improving release reliability.

HR Manager

Apr 2024 - Present

The Snippet App

Led full-cycle recruitment, onboarding 15+ developers and designers.
Streamlined team workflows, boosting productivity by 20%.

Leadership & Responsibilities

Founder & Executive Director

Aug 2024 - Present

Student Developers Cell - CIT

Established and grew a tech community; organized 30+ hackathons, speaker sessions, and code sprints.
Focused tracks across AI/ML, Web Dev, and Cloud for hands-on learning culture.

Skills: Community Building, Event Management, Strategic Planning, Tech Evangelism

Secretary

Apr 2024 - Sep 2024

Google Developer Student Clubs, CIT

Streamlined club operations by coordinating events and managing communications.
Ensured seamless execution of guest lectures and collaborative initiatives.

Skills: Operations Management, Stakeholder Coordination, Event Logistics, Internal Communication

Co-Chairperson, Innovation Vertical

Jul 2023 - Dec 2024

YI YUVA, CIT

Designed and executed innovation challenges and mentorship programs.
Empowered students to create, innovate, and invent while bringing YUVA vision to campus.

Skills: Program Design, Mentorship, Cross-functional Collaboration, Creative Strategy

Head of Innovation

Aug 2023 - Apr 2024

Google Developer Student Clubs, CIT

Led ideation and delivery of 10+ workshops and internal hackathons on AI/ML and web development.
Mentored teams on prototype building and drove a culture of experimentation.

Skills: Innovation Leadership, Technical Mentorship, Workshop Facilitation, Prototype Development

Expertise

Languages: Python, SQL, TypeScript, JavaScript, C, R, Dart, HTML/CSS ML/AI: PyTorch, TensorFlow, Keras, Scikit-learn, Transformers, DistilBERT, KeyBERT GenAI & Agents: LangChain, Prompt Engineering, OpenAI API, Gemini, Groq API CV & NLP: YOLOv8, OpenCV, Tesseract OCR, Sentiment Analysis, Recommender Systems Web & App: FastAPI, React, Node.js, Flask, Streamlit, Vite, Flutter, Riverpod Cloud/DB: AWS, SageMaker, AWS Glue, MySQL, PostgreSQL, MongoDB, pgvector, SQLite, SQLAlchemy Tools & Infra: MLflow, Power BI, Docker, Docker Compose, Git, Playwright, SSE Core: Data Pipelines, MLOps, QA Automation, Time-Series Modeling, LLM Integrations, API Design

Publications & Writing

Revolutionizing Genomics with Deep Learning

ICETST 2025, Coimbatore

View Proceedings

Technical Writing on Medium

2 published articles on NLP and recommendation systems

Explore Articles

Blogs / Idea Lab

I write about AI where product realism, human behavior, and technical depth collide.

These essays break down practical machine learning problems in plain language, while still respecting the engineering nuance behind production-grade AI systems.

Recommendation Systems 14 min read

Can ML Predict When You'll Get Tired of Your Current Favorite Genre or Artist?

Exploring boredom modeling, behavior signals, and personalization drift across streaming systems using ML and recommender strategy.

Read Article

NLP 4 min read

Why AI Models Might Misinterpret Ancient Proverbs?

A practical take on why large language models often fail on figurative and culturally dense expressions, and what culture-aware context handling could look like in real NLP systems.

Read Article

AI & Society 10 min read

When Thinking Becomes Optional

A deep dive into cognitive offloading, AI-assisted reasoning, and how humans are evolving into biological interfaces for machine intelligence in the prompt-driven era.

Read Article

In Pipeline

Upcoming deep dives: model interpretability, GenAI architecture trade-offs, and real-world ML system design patterns.

Follow on Medium

Explore All Articles

Projects / Ship Log

I build ambitious products across GenAI, applied ML, and resilient software systems.

From research-heavy models to production-grade platforms, each build is designed to solve real problems with clear engineering trade-offs and strong execution discipline.

Featured Build

SZN QA

Orchestrated a parallel multi-agent testing architecture with 6 autonomous browser agents to validate core product flows and UI/UX behavior in under 3 minutes. Integrated Gemini for PRD-to-test generation, live progress via SSE, and a 100-point reliability scoring framework with screenshot-based evidence.

Tech Stack: TypeScript, React, Node.js, Vite, Playwright, Gemini, SSE

Why this is high-impact

6 autonomous browser agents executing in parallel.
Natural language PRD interpretation for dynamic test generation.
Evidence-backed reliability scoring to accelerate release decisions.

View Repository

Bioinformatics

Predicting DNA-Protein Binding Motifs

Designed a dual-module deep learning pipeline for motif prediction in genomic sequences with a Variational Autoencoder for synthetic sequence generation and a CNN classifier for binding property prediction.

Tech Stack: Python, TensorFlow, Keras, NumPy, Deep Learning

View Repository

NLP

Customer Sentiment Analysis Dashboard

Built a multilingual sentiment dashboard with DistilBERT and KeyBERT, including threaded real-time processing and interactive Streamlit visualizations for regional sentiment tracking.

Tech Stack: Python, Streamlit, Transformers, DistilBERT, KeyBERT, Matplotlib

View Repository

Conversational AI

SQL Chatbot for Database Interaction

Developed an NL-to-SQL chatbot using Groq LLaMA3 and LangChain agents that handles nested logic, aggregates, and filters to make relational data accessible for non-technical users.

Tech Stack: Python, LangChain, MySQL, Streamlit, Groq API, Prompt Engineering

View Repository

Computer Vision

License Plate Detection and Recognition

Created an ALPR system using YOLOv8 detection and Tesseract OCR, trained on a custom-annotated dataset and deployable as a lightweight Streamlit interface.

Tech Stack: YOLOv8, OpenCV, PyTorch, Tesseract OCR, Python, Streamlit

View Repository

Mobile App

Cross-Platform Meal Planner

Designed a cross-platform planner using location, preferences, and dietary goals with offline SQLite tracking, RSS food updates, and personalized grocery recommendations.

Tech Stack: Flutter, Dart, SQLite, REST APIs, Riverpod, Email Auth, RSS Feeds

View Repository

Time-Series AI

TSFM: Feature-Bootstrapped Masked Time-Series Pretraining

Architected a self-supervised transformer encoder with RevIN normalization and Conv1d patchification, scaling to process 10M+ time-series points and reducing reconstruction error through masked patch optimization.

Tech Stack: Python, PyTorch, sktime, Transformers, RevIN

View Repository

AI + Data Viz

AI based Chart Generator

Built a FastAPI-backed analytics assistant that turns natural language requests into Plotly charts with support for CSV, JSON, XLSX uploads and export-ready visuals.

Tech Stack: FastAPI, Python, Plotly, LLM Integration, JavaScript, HTML/CSS

View Repository

FinTech + GenAI

SFN

Built a full-stack financial reconciliation platform with a hybrid matching engine combining rule-based logic, pgvector similarity search, and LLM tie-breaking for traceable and faster reconciliation.

Tech Stack: React, Vite, FastAPI, PostgreSQL, pgvector, SQLAlchemy, OpenAI API, Docker

View Repository

I architect scalable software, orchestrate agentic systems, and ship workflows that deliver real-world value.

Sarvesh PV · AI/ML Engineer

Founder. Technocrat. Wordsmith. Mentor.

Education

Professional Experience

ML Engineer Intern

HR Manager

Leadership & Responsibilities

Founder & Executive Director

Secretary

Co-Chairperson, Innovation Vertical

Head of Innovation

Expertise

Publications & Writing

I write about AI where product realism, human behavior, and technical depth collide.

Can ML Predict When You'll Get Tired of Your Current Favorite Genre or Artist?

Why AI Models Might Misinterpret Ancient Proverbs?

When Thinking Becomes Optional

In Pipeline

I build ambitious products across GenAI, applied ML, and resilient software systems.

SZN QA

Predicting DNA-Protein Binding Motifs

Customer Sentiment Analysis Dashboard

SQL Chatbot for Database Interaction

License Plate Detection and Recognition

Cross-Platform Meal Planner

TSFM: Feature-Bootstrapped Masked Time-Series Pretraining

AI based Chart Generator

SFN

Let's build something useful, fast, and impossible to ignore.

Email is the shortest path to execution.