Skip to content
View YEsh-DEV's full-sized avatar
🎯
Focusing
🎯
Focusing
8 followers · 9 following

Highlights

  • Pro

Block or report YEsh-DEV

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
YEsh-DEV/README.md

Yeshwanth Atmakuri

AI engineer: agents, voice AI and GraphRAG

I teach AI to retrieve, speak and act.

3 internships in 2026 across voice AI, security research and automation. 2x Smart India Hackathon internal qualifier.

Now: AI Automation R&D Intern at Advfiction.

*Last seen: pushing to Vectorless-Rag, 12 days ago.*

Portfolio  |  LinkedIn  |  Email

Voyage

2026 timeline. Work and research: AI Automation R&D Intern at Advfiction from August; Research Intern in cyber threat intelligence, May to July; AI Engineering Intern at Simsy AI, January to March. Study and community: exchange semester at Universiti Teknologi Malaysia, March to August; member of McCarthy Lab, Next Tech Lab, ongoing.

Projects

Next-TTP: predicts an attacker's next technique with graph RAG. 41.38% Hits@1. Nexi: voice assistant grounded in PDFs and structured data. 340 ms voice replies. Palm Vein Pay: pay with your palm on a Raspberry Pi 5. Under 500 ms authentication. Recovery Agent: diagnoses failed payments and sends the fix itself. Drop-in middleware.

Click a card to open the repo. The gold ribbon marks today's island of the day.

Armory

Tech stack by category. Languages: Python, C++, Java. Frontend: HTML, CSS, JavaScript, TypeScript, React. Backend: FastAPI, SQLAlchemy, LiveKit, REST API, Webhooks. AI and ML: PyTorch, TensorFlow, scikit-learn, XGBoost, OpenCV, MediaPipe, LangChain, LangGraph, LlamaIndex, CrewAI, Advanced RAG. Cloud and deployment: Docker, AWS, GitHub Actions, Vercel, Git. Databases: Neo4j, ChromaDB, Qdrant, PostgreSQL, SQLite.

Gold marks the tools I use most.

Directions are optional. Shipping is not.

Pinned Loading

  1. nexi-ntl nexi-ntl Public

    voice driven AI assistant to help university students get quick and accurate answers to their queries about their campus life, Retrieval-Augmented Generation pipeline to provide information from ba…

    Python

  2. Next-TTP-Prediction Next-TTP-Prediction Public

    A Temporal-Causal GraphRAG architecture for Advanced Persistent Threat (APT) Next-TTP prediction using actor-aware knowledge graphs and RotatE embeddings.

    Python

  3. Cyber-Threat-Intelligence- Cyber-Threat-Intelligence- Public

    Python

  4. vein-detection vein-detection Public

    An edge-native Palm Vein Biometric Payment System on Raspberry Pi 5 — NIR 850nm imaging pipeline with MediaPipe hand landmarking, 2D Gabor wavelet VeinCode generation, and a 2-layer parallel MNHD s…

    Python 1

  5. Autonomous-Recovery-Agent Autonomous-Recovery-Agent Public

    Autonomous AI revenue recovery engine for Razorpay. Intercepts payment failures, enforces deterministic RBI guardrails, and recovers lost TPV over UPI & WhatsApp in <60s.

    Python