close
Skip to content
View Sahil0015's full-sized avatar

Highlights

  • Pro

Block or report Sahil0015

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
Sahil0015/README.md

Header

👋 Hey there, I'm Sahil Aggarwal

🚀 AI Backend Intern at Draup | Ex-Generative AI Intern at Infogain | IIIT Ranchi ’26 | Building scalable AI systems, production-grade backend, and applied LLM products

Profile Views GitHub Followers


🧑‍💻 About Me

Coding

  • 🎓 Final-year B.Tech CSE student at IIIT Ranchi (Batch of 2026)
  • 🧠 Building AI systems with LLMs, RAG, and multi-agent workflows
  • ⚙️ Working on enterprise Django backends, DRF APIs, JWT auth, and observability
  • 🔬 Researching LLM alignment, fine-tuning, and multilingual evaluation
  • 🧩 Interested in voice agents, LLM evaluation frameworks, and scalable AI architecture
  • 📝 Sharing technical insights on AI/ML, backend engineering, and applied systems
  • 🤝 Open to collaboration on AI products, research, and backend engineering

🌐 Connect With Me

Image Image Image Image


✍️ Latest Blog Posts & Writing

I regularly write about AI, Machine Learning, and LLMs on Medium. Check out my latest articles:

Medium Blog

📝 Topics I write about:

  • 🤖 Generative AI & Large Language Models
  • 🧠 Multi-Agent Systems and LLM orchestration
  • 🔍 RAG Pipelines & Hybrid Retrieval techniques
  • 💡 Applied AI tutorials and project breakdowns
  • 🛠️ MLOps best practices and production deployments

💭 "Sharing knowledge is the best way to solidify understanding"


🌟 Open Source & Research Contributions

🔬 Research Work

  • 🔬 Indian Languages NLP Research: Contributed to dataset curation (co-authored 700-entry bilingual dataset, ICLR 2025 submission) and experiments for Sanskrit, Marathi, and Hindi NLP systems (e.g., fine-tuned Whisper for Hindi speech-to-text in EchoScript) [file:1]
  • 📊 Developed multilingual LLM evaluation and benchmarking frameworks, assessing open-source models on alignment, cross-lingual robustness, and post-training effects using Hugging Face datasets [file:1]
  • 🧪 Built and explored novel hybrid retrieval systems (e.g., ResearchMind with Cohere Rerank and semantic caching; MedGuide RAG pipeline improving accuracy by 30%) for specialized domains like arXiv analysis and medical reports [file:1]

💻 Open Source Contributions

  • 🤝 Active contributor to AI/ML open-source projects on GitHub
  • 🧩 Building reusable components for LLM applications and agent frameworks
  • 📦 Sharing tools and utilities for the AI developer community
  • ⭐ Check out my repositories to see what I'm working on!

Open Source Love PRs Welcome


💼 Portfolio & Projects

🔗 Explore my AI projects and implementations:
👉 GitHub Repositories


🤝 Open to Opportunities

I'm actively seeking opportunities to collaborate and grow in the AI/ML space:

🤝 Collaborations
Open-source projects, research papers, AI/ML initiatives
💼 Job Opportunities
Generative AI, NLP Engineer, ML Engineer roles
🔬 Research Projects
Applied AI, Multi-Agent Systems, LLM applications
🎤 Speaking & Mentoring
Workshops, technical talks, knowledge sharing

📬 Feel free to reach out at sahilaggarwal1532003@gmail.com


🛠️ Tech Stack

🚀 Programming Languages

Image

🧠 AI / ML / Data Science

Image Image Image Image Image Image Image Image Image Image

🧱 Backend / Databases / Infra

Image Image Image Image Image Image Image Image Image

🛠️ Tools

Image Image Image Image Image


🔭 Featured Projects & Work

🧠 EchoScript

View Project

Hindi speech-to-text pipeline using Whisper fine-tuning, transcript cleanup, and error-aware post-processing for cleaner downstream analytics and LLM workflows.

💊 MedGuide

View Project

RAG-powered multi-agent system for lab report interpretation, reducing analysis time by 80% and improving retrieval accuracy by 30%.

🚀 Current Work

  • 🧩 Contributed to experimental NLP research on multilingual models for Sanskrit and Marathi datasets
  • 🧠 Exploring advanced LLM orchestration with LangGraph, CrewAI, and Agno
  • 🔬 Building evaluation frameworks for multi-agent systems and RAG pipelines
  • 📝 Writing technical blogs on AI, backend engineering, and applied LLM systems

🧰 Tech Stack

Category Tools / Frameworks
Languages Python, C++, C, SQL
Backend Django, Django REST Framework, FastAPI
AI / ML Frameworks PyTorch, TensorFlow, LangChain, LangGraph, CrewAI, Agno
Databases PostgreSQL, MySQL, LanceDB
Libraries Scikit-learn, Pandas, NumPy, Hugging Face, OpenCV
Deployment Docker, Streamlit, FastAPI
Tools GitHub, VSCode, Jupyter Notebook, Google Colab, Kaggle, Postman, Jira
Cloud / Infra AWS, Docker, Linux
Domains Generative AI, LLMs, NLP, Applied AI, Multi-Agent Systems, Deep Learning

🧩 Career Highlights & Achievements

🚀 Professional Experience
  • 🧠 AI Backend Intern at Draup
    Working on enterprise backend systems with Django, DRF, JWT authentication, and observability, while contributing to production AI workflows
  • 🤖 Ex-Generative AI Intern at Infogain
    Built UIBot, a GenAI assistant that generated UI components and test suites, reducing manual UI/QA cycles by 15%
  • 🔬 Student Research Intern at Pragya Lab
    Researching post-training LLM alignment, multilingual behavior, and base vs instruct model performance through structured experiments
🔬 Research & Open Source
  • 🇮🇳 Indian Languages NLP Research Contributor
    Contributing to dataset curation and experiments for Sanskrit and Marathi language systems
  • 📊 Multilingual LLM Evaluation
    Working on benchmark-driven evaluation of LLMs across multilingual and cross-lingual settings
  • 💻 Open Source Contributor
    Contributing to AI/ML projects and building reusable components for LLM applications, agent workflows, and RAG systems
🏆 Selected Achievements
  • 🧠 Built ResearchMind, a production-grade multi-agent RAG system for arXiv paper analysis
  • 💊 Built MedGuide, a RAG-powered medical interpretation system that improved retrieval accuracy by 30%
  • ⚖️ Shortlisted in the Global Agent Hackathon for Legalia.AI, an AI courtroom simulator
  • 📝 Published technical blogs and reached 500+ total views
  • 💪 Solved 800+ coding problems across platforms including LeetCode, CodeChef, and GFG
💪 Competitive Programming

Solved 800+ coding problems across multiple platforms:

LeetCode Code360 GFG CodeChef

🎯 Leadership & Community
  • 🏅 Active member of House of Geeks and ACM IIIT Ranchi
  • 🎤 Organizing technical workshops and events
  • 👥 Mentoring juniors in AI/ML and competitive programming

💭 "Exploring how intelligent systems perceive, reason, and act."


🌟 Support My Work

If you find my projects helpful or interesting:

  • Star my repositories
  • 🔔 Follow me on GitHub for updates
  • 🤝 Collaborate on open-source projects
  • 💬 Share with others who might benefit
  • 📝 Read and share my Medium articles

Footer

⭐ If you find my work interesting, consider starring my repositories!
🤝 Open to collaborations, research opportunities, and job roles in AI/ML


Made with ❤️ and lots of ☕ by Sahil Aggarwal
💼 Currently exploring opportunities in Generative AI & NLP | 🌐 Let's build something amazing together!

Pinned Loading

  1. global-agent-hackathon-may-2025 global-agent-hackathon-may-2025 Public

    Forked from global-agent-hackathon/global-agent-hackathon-may-2025

    A month-long, open-source AI Agent Hackathon — open to all builders and dreamers working on agents, RAG, tool use, and multi-agent systems.

    Python

  2. MedGuide MedGuide Public

    AI-powered health report assistant that analyzes blood and lab test reports using multi-agent reasoning, hybrid RAG (LanceDB + Cohere), and LLMs to generate structured medical insights and contextu…

    Python

  3. TumorNet TumorNet Public

    Jupyter Notebook

  4. global-agent-hackathon/global-agent-hackathon-may-2025 global-agent-hackathon/global-agent-hackathon-may-2025 Public

    A month-long, open-source AI Agent Hackathon — open to all builders and dreamers working on agents, RAG, tool use, and multi-agent systems.

    247 98

  5. Conversational_History_RAG_with_PDF Conversational_History_RAG_with_PDF Public

    Python

  6. Twitter_Sentiment_Analysis Twitter_Sentiment_Analysis Public

    Jupyter Notebook