Rioneel (Raguveer Reddy) · GitHub
Skip to content
View Rioneel's full-sized avatar
🎯
Focusing
🎯
Focusing
1 follower · 1 following

Highlights

  • Pro

Block or report Rioneel

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.

Content in all repositories owned by your account will be closed.
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
rioneel/readme.md

Hey, I'm rioneel👋

AI/ML Engineer · Embedded Systems · Multi-Agent Robotics Research

Typing SVG

👨‍💻 About me

  • 🚀 Building aspirefit.in
  • 🌱 Currently deep in self-hosted inferencing and AI System Design
  • 🤖 Building production AI infrastructure — self-hosted LLM serving, multi-stage inference pipelines, agentic systems with tool-calling and long-term memory
  • 🛰️ Background in embedded systems & aerospace — designed flight software and gyro/reaction-wheel stabilization for a CanSat that won an Excellent Grade at the ISRO–IN-SPACe National CanSat Competition
  • 🧠 Published researcher — co-authored "Decentralized Swarm Rovers for Planetary Surface Exploration" at GLEX 2025, on multi-agent RL (MADDPG/MAPPO) for Mars rover swarms; patent pending on the underlying architecture

🛠️ Tech Stack

Languages & Core

AI / ML

Backend & Data

Embedded & Robotics

Tools

🔬 Also working with

vLLM Qwen2.5-VL / Qwen3 RunPod Model Context Protocol (MCP) Supermemory LLM Fine-tuning (LoRA) RAG MADDPG MAPPO YOLOv9 ConvNeXt EKF / Visual SLAM Fiber pgx/pgxscan

(niche infra without standard logos — self-hosted LLM serving, agentic tool-calling frameworks, and multi-agent RL algorithms)

🏆 Publications & Achievements

  • 📄 Research Paper — Decentralized Swarm Rovers for Planetary Surface Exploration, GLEX 2025
  • 🔖 Patent (pending) — Decentralized swarm rover system architecture and algorithms
  • 🥇 ISRO–IN-SPACe National CanSat Competition — Excellent Grade, Top Performance (619.7m altitude, real-time telemetry, onboard AI anomaly detection)
  • 🛰️ Software Lead, Team Tejas / Team Indus — satellite payload & mission control systems (InSPACe, American CanSat)

📫 Reach me

Pinned Loading

  1. social social Public

    a social media platform written in go . This project has been made to teach myself go, the backend is in go std net/http lib.

    Go

  2. reward-system-for-trustworthy-medical-federated-learning reward-system-for-trustworthy-medical-federated-learning Public

    A working prototype of a federated evaluation and reward system for medical imaging. Multiple simulated hospital clients run local inference using a pretrained DenseNet-121, while a central server …

    Python

  3. LAM-KALIVEGA/ALFR LAM-KALIVEGA/ALFR Public

    An ALFR robot which is fast and agile tuned for sharp cuts and massive curve turns, highly tested with built in lost and recovery mode with 450ms.

    C++

  4. ai-tutor-orchestrator-mvp ai-tutor-orchestrator-mvp Public

    Minimal, runnable MVP for a priority-based orchestrator with parameter extraction, schema validation, and integration with two mock tools (Quiz, Flashcards).

    Python

  5. circle-app circle-app Public

    Circle — a trust-network recommendation app built on CognoDB (Neo4j-compatible graph DB). Instead of star ratings, it ranks service providers by how your own trust network — friends, friends-of-fri…

    Go