Skip to content
View AnuragRaut08's full-sized avatar
🏠
Working from home
🏠
Working from home
  • 18:01 (UTC +05:30)

Block or report AnuragRaut08

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
AnuragRaut08/README.md

Hi, I'm Anurag Raut πŸ‘‹

AI Engineer | Data Engineer | Machine Learning Enthusiast

Anurag Raut Banner

πŸŽ“ Final-year B.Tech student at VIT Pune, passionate about building intelligent, scalable, and real-world AI systems.

πŸš€ Areas of Focus

  • Applied Machine Learning | Deep Learning | Generative AI (LLMs) | Data Engineering
  • Hands-on with building end-to-end ML pipelines, LLM-based systems, and production-ready backend services

πŸ› οΈ What I Do

  • 🧠 ML/NLP Systems – Multilingual understanding, Named Entity Recognition (NER), Summarization, Knowledge Graph Generation
  • πŸ› οΈ Backend Development – Production-grade systems including FastAPI, Flask, Docker, and PostgreSQL
  • πŸ“Š Data Engineering – Real-time ETL pipelines using Airflow, Pandas, SQL, and ClickHouse
  • πŸŽ™οΈ Speech & LLMs – Leveraging ASR and transformers for real-time speech-to-text, translation, and legal document automation

πŸ“š Research & Publications

  • πŸ“ Published in Springer Nature and IEEE
  • πŸ” Topics: Multilingual NLP, YouTube Video Summarization, Legal Tech Automation using AI

πŸ’‘ Core Belief

"I’m passionate about crafting AI-driven systems that create tangible impact β€” from streamlining workflows to enabling smarter, data-driven decisions."


πŸ› οΈ Tech Stack


🧠 AI & Machine Learning
  • Frameworks: PyTorch, TensorFlow, scikit-learn, Hugging Face Transformers
  • Techniques: LLMs, NER, RAG, CNNs, RNNs, ASR, Cross-lingual Summarization
  • Toolkits: spaCy, OpenCV, NLTK, Librosa
πŸ“Š Data Engineering
  • Pipelines: Apache Airflow, Pandas, SQL, Kafka (intro), ETL/ELT Architecture
  • Databases: PostgreSQL, AmazonS3, Redshift, BigQuery, DuckDB, MongoDB, MySQL, ClickHouse, Neo4j, OrientDB
πŸ› οΈ Backend & DevOps
  • Frameworks: FastAPI, Flask, Node.js
  • Deployment: Docker, GitHub Actions, AWS (EC2, S3), GCP, Azure, Nginx, Kubernetes (intro)
🌐 Frontend Development
  • Tech: React.js, Next.js, Flutter, HTML/CSS, TailwindCSS
  • UI/UX Tools: Figma, Canva
🧰 Developer Tools
  • Version Control & IDEs: Git, GitHub, GitLab, VS Code
  • Others: Postman, Jupyter Notebooks, Google Colab, Notion, Linux Shell

🧩 Domains I Love

  • πŸ” Information Retrieval & NLP
    Semantic search, transformers, embeddings, and text summarization for real-world use cases

  • βš–οΈ Legal Tech & Accessible AI
    Democratizing justice with LLMs, NER pipelines, and multilingual legal document processing

  • πŸ“Š Data Engineering & Systems Design
    Scalable ETL pipelines, real-time data streaming, and analytics-driven system architecture

  • πŸ“š Multilingual AI & Generative Applications
    Speech-to-text, translation, cross-lingual summarization, and zero-shot learning using LLMs

  • 🧠 LLM Fine-tuning & Retrieval-Augmented Generation (RAG)
    Building smart Q/A systems and task-specific copilots using LangChain, FAISS, and custom prompts

  • 🧩 Graph Databases & Knowledge Graphs
    Neo4j, OrientDB, entity linking, and relationship extraction for graph-based reasoning

  • πŸŽ™οΈ Speech & Audio Intelligence
    ASR, voice-based interfaces, audio pre-processing, and multilingual speech conversion

  • πŸ§ͺ Model Deployment & MLOps
    CI/CD for ML, Docker-based deployments, model monitoring, and FastAPI microservices

  • πŸ” Ethical AI & Responsible Tech
    Focused on fairness, accessibility, explainability, and real-world impact of AI systems


πŸ“« Reach Out


β€œMaking AI usable, scalable, and truly impactful.”

Popular repositories Loading

  1. Rolling-the-Dice-on-DevOps Rolling-the-Dice-on-DevOps Public

    CI/CD and Kubernetes for a Board Game Web App

    Dockerfile 1

  2. Legal-Eagle Legal-Eagle Public

    EDI-Sem5

    Python

  3. -LinguaFlux -LinguaFlux Public

    Python

  4. AI-Agent AI-Agent Public

    The Data Display component shows extracted information in a table format and allows users to download data or sync with Google Sheets.

    Python

  5. CredSync CredSync Public

    Streamlined Financial Management & Credit Card Spending Analysis

    TypeScript

  6. ecommercebackend ecommercebackend Public

    Forked from thelegendaryarticuno/ecommercebackend

    The backend for eccomerce

    HTML