Skip to content
View DevanshSrajput's full-sized avatar
🏠
Working from home
🏠
Working from home
19 followers · 14 following

Achievements

Achievement: StarstruckAchievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: YOLOAchievement: Quickdraw

Achievements

Achievement: StarstruckAchievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report DevanshSrajput

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
DevanshSrajput/README.md 
class DevanshSinghRajput:  # SRM-IST Delhi-NCR · B.Tech CSE '27 · CGPA 8.91
    role       = "Research Intern @ IIT(ISM) Dhanbad"
    building   = ["Edge AI on Jetson", "Multi-agent pipelines", "NLP fairness research"]
    shipped    = ["HiSLM", "NexusPay", "Dataa_Analyst_Agent ⭐21", "FleetTax", "SignalHire"]
    selected   = ["Amazon ML Summer School '25", "GSSoC", "Auto-Coder Hackathon 🥈"]
    open_to    = ["ML Engineering", "Data Science", "Research Collabs"]
    philosophy = "Ship real things. Don't claim tools without GitHub evidence."

Featured Projects

Projects — HiSLM, NexusPay, Dataa_Analyst_Agent, SignalHire, Learning Agent, Hindi-Toxicity-Bias, FleetTax

Tech Stack

Tech Stack

GitHub Stats

 



GitHub Streak

Connect

Portfolio   GitHub   LinkedIn   Email


footer

Pinned Loading

  1. Dataa_Analyst_Agent Dataa_Analyst_Agent Public

    AI-powered Streamlit app for analyzing, summarizing, and chatting with documents (PDF, DOCX, CSV, images, etc.) using LLMs and Together AI.

    Python 25 2

  2. SignalHire SignalHire Public

    Unsupervised AI candidate ranking system — hybrid rule-based scoring + semantic embeddings over 100K profiles. Built for the Redrob AI challenge (India Runs Hackathon 2025).

    HTML 6 3

  3. Learning-Agent-System Learning-Agent-System Public

    AI-powered tutoring platform with checkpoint-based learning, adaptive assessment, and Feynman Technique simplification using LangGraph and Ollama

    Python 1

  4. Hybrid_Recommendation_System Hybrid_Recommendation_System Public

    An AI-powered movie recommendation engine combining collaborative filtering, content-based filtering, and hybrid approaches. Built with Streamlit for an interactive web experience. 🚀 Features: real…

    Python 2 2

  5. NexusPay NexusPay Public

    NexusPay is a reference implementation of an autonomous, budget-aware AI agent that buys its own data over the x402 HTTP payment protocol. You ask a question; it plans which paid sources to buy (Ge…

    Python 1

  6. HiSLM-Jetson-AGX-Orin HiSLM-Jetson-AGX-Orin Public

    Hierarchical SLM inference on NVIDIA Jetson AGX Orin. Runs Qwen2.5-3B via llama.cpp with CUDA acceleration, served over Tailscale VPN to an Orin NX wireless client.

    Python 1