Skip to content
View rahulthota21's full-sized avatar
1 follower · 1 following

Achievements

Achievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: YOLO

Highlights

  • Pro

Block or report rahulthota21

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
rahulthota21/README.md

Thota Rahul

Backend & AI Agent Engineer
Building high-performance APIs, async microservices, and autonomous AI systems.

 

💻 Primary Tech Stack

Category Tools & Technologies
Languages Python, SQL (PostgreSQL), MongoDB
Backend & Infra FastAPI, REST APIs, Redis, Supabase, Docker
AI & Agents LangGraph, RAG Pipelines, FAISS, Scikit-learn, XGBoost

⚙️ Core Architecture Projects

🏥 HealthATM

On-Device 3D Nodule Detection & Voice Agent

  • INT8 MobileUNet3D (0.32MB) on-device inference.
  • Async scan queuing with FastAPI & Redis/RQ.
  • LangGraph ReAct agent & 10+ language voice AI.

🎯 Mock'n-Hire

Microservices AI Screening Engine

  • Automated shortlisting with 86.4% Precision@10.
  • Mistral-8x7B ranking & Sentence Transformers.
  • Supabase auth, DB, & Object Storage microservices.

🧠 AffectLearn

Sentiment-Aware Adaptive Tutoring Engine

  • LoRA fine-tuned TinyLLaMA for adaptive lesson flow.
  • Multimodal emotion processing (CNN + Whisper).
  • FAISS vector indexing on OpenStax textbooks.

📑 IEEE Research Publications

Peer-Reviewed AI Implementations

  • HealthATM: 3D Nodule Detection Distillation
  • Mock'n-Hire: Automated Screening Engine
  • AffectLearn: Adaptive Tutor with LoRA LLMs

🎯 Key Focus Areas

  • Async Microservices: Designing asynchronous APIs using FastAPI, Redis task queues, and background workers.
  • Agentic AI Workflows: Building LangGraph agents with dynamic tool execution and reasoning capabilities.
  • Model Optimization: Quantizing deep learning models to run efficiently on CPU devices without GPUs.

Pinned Loading

  1. AffectLearn AffectLearn Public

    AffectLearn is an AI-powered tutoring platform that senses a learner’s emotions and adapts explanations, quizzes, and tone in real time - merging LoRA-tuned models, multimodal emotion recognition, …

    TypeScript

  2. EcoSphere-AI EcoSphere-AI Public

    EcoSphere AI delivers real-time, global housing risk intelligence—forecasting floods, heatwaves, and droughts - to help planners, policymakers, and families build safer, climate-resilient communities.

    HTML

  3. Mock-n-Hire Mock-n-Hire Public

    Mock’n-Hire redefines hiring end-to-end by ranking resumes with semantic precision and delivering real-time, emotion-aware mock interview feedback - giving recruiters bias-resistant insights and ca…

    TypeScript

  4. healthatm-backend healthatm-backend Public

    Python