V.
VIGHNESH KUMBHAR01 / 01

AI ENGINEER / DEVELOPER
PUNE, INDIA

B.E. MECHANICAL ENGINEERING
AISSMS COE / 2028

EngineeringIntelligence.

Designing and building intelligent systems that solve real-world problems.

SCROLL TO EXPLORE

Machine Learning
Generative AI
AI Systems
Software Engineering

About me.

I am an engineering student exploring the intersection of artificial intelligence, software engineering, and real-world systems.

My interests lie in understanding how intelligent systems work, how they can be orchestrated, and how complex technical ideas become practical products. I believe in building, experimenting, questioning assumptions, and learning through implementation.

EDUCATIONB.E. Mechanical Engineering
AISSMS College of Engineering, Pune
DIRECTIONMachine Learning / Generative AI
Agents / Systems Architecture
APPROACHUnderstand deeply.
Build deliberately. Measure honestly.
GRADUATING2028
Exploring the distance between idea and system.

Loading public activity...

01 / 03

Learning.
Building.
Evolving.

2024

FOUNDATIONS

Programming, software development, and engineering fundamentals.

Early software work
2025

EXPERIMENTATION

Web development, automation, AI tools, and independent projects.

Full-stack and tooling experiments
2026

INTELLIGENT SYSTEMS

Machine learning, neural networks, LLMs, agents, and system orchestration.

ISRO, Jarvis, Capsule, and systems work
02 / 03

What I work with.

PROGRAMMING

PythonJavaScriptTypeScriptC++

Languages visible across the audited repositories.

MACHINE LEARNING

NumPyPandasscikit-learnPyTorchXGBoost

Used in the space-weather and intercept-prediction work.

GENERATIVE AI

OllamaWhisperHugging FaceTransformersLLM interpretation

Local inference, voice systems, and model-serving experiments.

AI SYSTEMS

Agent workflowsTool executionMemoryProvider SDKsEvaluation

Explored through Jarvis and Capsule architecture.

BACKEND

Next.jsFastAPIREST APIsSupabaseSQL

Visible in the audited full-stack and API projects.

TOOLS

GitGitHubDockerVitePlaywright

Build, testing, packaging, and repository workflows.

The builds.

Seven projects. Different surfaces. One question: how does an idea become a working system?

03 / 03

Beyond the build.

01

Context efficiency for LLM applications

OBJECTIVE
How can context operations become reusable system primitives?

APPROACH
Token budgeting, semantic deduplication, ranking, provider boundaries, and package composition.

Read source
02

Physics-informed forecasting

OBJECTIVE
How should physical signals become features for multi-horizon prediction?

APPROACH
Solar electron-flux data, physics-informed features, classical ensembles, and neural models.

Read source
03

Local voice agents

OBJECTIVE
What modules are required between speech input and a safe system action?

APPROACH
Whisper transcription, Ollama inference, memory, plugins, executor boundaries, and speech output.

Read source
04

Embedded intelligence

OBJECTIVE
How can software signals reflect a physical-world state?

APPROACH
ESP32 firmware, sensor modules, local storage, cloud sync, and caregiver-facing interfaces.

Read source
LET'S CONNECT

Let's build something.

Open to collaboration, interesting problems, and engineering opportunities.