Skip to content
View pranaysb's full-sized avatar
  • Bengaluru Urban, India
  • 16:00 (UTC -12:00)
  • LinkedIn in/pranaysb

Block or report pranaysb

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pranaysb/README.md

Applied AI Engineer • Vision AI • Agentic Systems • ML Engineering

Building deployable AI systems — from computer vision and multimodal intelligence to agentic workflows and production-ready ML systems.

IIT Bhilai   •   Research @ IIT Hyderabad   •   Founder @ Optisense AI


About Me

Focus

  • Building Applied AI systems that move beyond notebooks
  • Working on Vision AI, multimodal intelligence, and LLM systems
  • Designing agentic workflows and intelligent automation systems
  • Developing end-to-end ML systems with deployment in mind

Background

B.Tech Electrical Engineering
Indian Institute of Technology Bhilai

AI/ML Research Intern
Visual Intelligence & Learning Lab, IIT Hyderabad

Founder — Optisense AI
Building AI-powered smart infrastructure systems


Current Focus

Building Exploring Learning
Vision AI Systems Agentic Workflows MCP
Full-Stack AI Apps LLM Automation LangGraph
Edge AI & Real-Time Inference Retrieval Systems Production ML
ML Pipelines AI Evaluations Multi-Agent Systems

Currently Building

→ Agentic AI Systems
→ Vision-Language Applications
→ Production ML Pipelines
→ Real-Time Edge AI Systems
→ Deployable Full-Stack AI Products

Building

Optisense AI

AI-driven smart infrastructure startup focused on:

  • Automatic Number Plate Recognition (ANPR)
  • Smart Parking Systems
  • Edge AI Deployment
  • Real-Time Monitoring
  • Intelligent Vision Systems

Agentic AI Systems

Building autonomous AI workflows using:

  • LLM Agents
  • MCP (Model Context Protocol)
  • Retrieval Systems (RAG)
  • Multi-Agent Systems
  • Tool Calling & Workflow Automation

Vision AI & Multimodal Systems

Working on:

  • Computer Vision
  • Visual Question Answering (VQA)
  • Scene Understanding
  • 3D Gaussian Splatting
  • Real-Time Inference Pipelines

End-to-End AI Products

Building deployable systems with:

  • FastAPI
  • React & Next.js
  • PostgreSQL & APIs
  • Dockerized Deployments
  • Full-Stack ML Workflows

Tech Stack

Languages

AI / Machine Learning

Backend & APIs

Frontend

Databases

DevOps & Infrastructure

Hardware & Embedded Systems


Areas of Interest

Applied AI Vision AI Agentic Systems ML Systems
Real-world AI products Scene understanding LLM agents Deployment
Intelligent automation Multimodal intelligence Workflow orchestration Scalable inference
Production systems Edge perception Tool use & orchestration Full-stack ML

GitHub Analytics




Connect

Building intelligent systems that move from research to real-world deployment.

Pinned Loading

  1. API-Forge-AI API-Forge-AI Public

    Autonomous generation of production-ready SDKs. Upload your OpenAPI spec. Watch our agents autonomously map dependencies, test endpoints, fix bugs, and generate production-ready SDKs.

    Python

  2. negoaitech negoaitech Public

    Forked from ujwal209/negoaitech

    TypeScript

  3. pranaysb pranaysb Public

    Config files for my GitHub profile.

  4. VQA-Blip-model VQA-Blip-model Public

    VQA

    Python