Skip to content
View amaan784's full-sized avatar
12 followers · 9 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Highlights

Block or report amaan784

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
amaan784/README.md

Hi, I'm Amaan

Machine learning and software engineer finishing an M.S. in Computer Science (Machine Learning track) at Columbia University. Graduating December 2026 and open to full-time roles. Previously an Applied AI Scientist Intern at ZS and a Software Engineer at Kenvue.

Website LinkedIn Google Scholar Hugging Face Devpost Kaggle Email

Highlights

  • 🏆 Best Use of Hugging Face at the Mistral Worldwide Hackathon, for ShadowVerse
  • 📄 Co-author of Beyond Static Leaderboards (under review at ACL) and a paper at the 2026 AIChE Annual Meeting
  • ⚡ About 2x lower VLM latency with INT4 quantization on IBM AssetOpsBench (code)
  • 🛡️ AI safety: Advanced Technical Fellow with the Columbia AI Alignment Club

Tech stack

ML and deep learning
Python PyTorch TensorFlow Hugging Face scikit-learn OpenCV

LLMs and agents
LangChain LangGraph MLflow Weights & Biases

Data
Apache Spark Databricks PostgreSQL Neo4j Apache Kafka

Cloud and apps
Azure AWS Google Cloud Docker FastAPI React

Selected projects are pinned below. More projects and publications on my website.

Pinned Loading

  1. dl4cv-final-project dl4cv-final-project Public

    Spatial and semantic scene graphs for retail shelves. RT-DETR and YOLOv11 (fine-tuned on SKU-110K) detect products, CLIP visual anchors classify brands by nearest-neighbor retrieval, and NetworkX b…

    HTML

  2. ai-news-analysis-raise-hackathon2026 ai-news-analysis-raise-hackathon2026 Public

    RAISE 2026 hackathon (Rutgers) submission by team Latent Space. NLP analysis of how news headlines frame AI: VADER sentiment and DistilRoBERTa emotion, a custom AI-Phobia score for alarmist framing…

    Jupyter Notebook

  3. active-clinical-guardian-devfest26 active-clinical-guardian-devfest26 Public

    Synapse doctor scriber for devfest 2026 at Columbia University

    Python 1

  4. exploring-curiosity/ShadowVerse exploring-curiosity/ShadowVerse Public

    Know how your users react before launching any new feature from their browser interactions. Tailored by you users and for your users.

    Python 2

  5. hpml-final-project hpml-final-project Public

    Vision add-on for IBM's AssetOpsBench: an AI agent that spots defects in photos of industrial equipment, with AI models compressed to run ~2x faster on a single low-cost GPU.

    Python 1

  6. pramana-care-ai pramana-care-ai Public

    Agentic data-quality engine for Indian healthcare, built at Hack-Nation's Global AI Hackathon (Databricks for Good). Scores 10K facility records against contradiction rules and answers planner ques…

    Python