Skip to content
View ImaadHasan2002's full-sized avatar
🎯
1.1% better everyday
🎯
1.1% better everyday

Highlights

  • Pro

Block or report ImaadHasan2002

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
ImaadHasan2002/README.md

GitHub LinkedIn X Blog Email

AI Research Engineer @ STARlab Capital

I build both foundational and refine existing AI systems for finance, healthcare and agritech ML workflows, with a focus on multimodal learning, retrieval pipelines, and scalable model deployment.

  • Currently: AI Research Engineer at STARlab Capital, working in finance and leading an agentic AI side project in agriculture field.
  • I write blogs at imaad.bearblog.dev.
  • Open to collaborating on impactful applied AI research projects.

GitHub Activity

GitHub contribution streak


Tech Stack

Languages

Python SQL C/C++ JavaScript HTML5 CSS3

Frameworks

TensorFlow PyTorch LangChain LangGraph Flask FastAPI Django Streamlit Keras

Cloud and MLOps

AWS EC2 Glue Lambda S3 SageMaker Bedrock Docker Jenkins MLflow Redis Prometheus Grafana Pinecone Git GitHub Linux PySpark

Developer Tools

Cursor VS%20Code PyCharm Vim Jupyter Spyder

Data and Libraries

Pandas NumPy Polars SciPy Scikit-learn Matplotlib Plotly OpenCV


Experience Snapshot

  • STARlab Capital — AI Research Engineer (Jul 2025 - Present)

  • STARlab Capital — AI Research Intern (Apr 2025 - Jun 2025)
    Leading R&D for ViviSTAR, building self-supervised WSI pipelines, optimizing slide visualization workloads, and supporting graph-based biomedical retrieval for LLM pretraining. Backtested multiple trading strategies by transforming intuition-based hyperparameters into mathematically grounded simulations.

  • Aavaaz.ai — AI Engineer, Part-time (Dec 2024 - Jan 2025, Remote)
    Designed back-translation and data-filtering pipelines for Azure STT models and trained CNN-based speech emotion recognition models across 12 languages.

  • Zenon Analytics — Predictive Software Intern (Jun 2024 - Aug 2024)
    Improved feature engineering runtime by 15% and integrated model interpretability in an AutoML production pipeline.


Education

  • Aligarh Muslim University (ZHCET)
    Bachelor of Technology (B.Tech), Artificial Intelligence
    CPI: 8.44/10 (GPA: 3.38/4.0)

  • Relevant Coursework
    Machine Learning, Artificial Intelligence, Deep Learning, NLP, Reinforcement Learning, Recommender Systems, Data Visualization, Image and Video Processing, Linear Algebra, Calculus.


Publications

  • AutoML, LLMs, Bayesian Optimization
    Hasan, I., Tausif, M. (2025). Designing an Interpretable and Efficient AutoML Pipeline for Enhanced Data Analytics. 2025 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), IEEE.
    DOI: 10.1109/ICSSAS66150.2025.11081354 | IEEE Xplore
    Combined deep feature synthesis, LLMs, and Bayesian optimization; achieved 10%+ performance gains across datasets belonging from healthcare, finance, telecom, and educational domains.

Pinned Loading

  1. Multi-Modal-Retinal-Fundus-Scan-Analysis Multi-Modal-Retinal-Fundus-Scan-Analysis Public

    Forked from FaisalKhan19/Multi-Modal-Retinal-Fundus-Scan-Analysis

    A Multi-Modal Approach for Multiclass Ophthalmic Disease Classification for Fundus Scan Images.

    Jupyter Notebook 2 1

  2. Low-Code-Chatbot-Builder Low-Code-Chatbot-Builder Public

    JavaScript 1

  3. Road-Segmentation-Object-Detection-using-Deep-Learning Road-Segmentation-Object-Detection-using-Deep-Learning Public

    In this project, a deep learning-based approach is used for lane detection on semi-urban roads. The proposed model consists of two main components: a CNN architecture, ResNet101, for semantic segme…

    Python 5 1

  4. AutoML-Pipeline AutoML-Pipeline Public

    An automated end-to-end machine learning pipeline in Python.

    Jupyter Notebook 1

  5. Zehnnflow Zehnnflow Public

    A versatile productivity suite designed to support individuals with ADHD and neurotypicals in achieving a focused and efficient workflow.

    Python 1