afftab.

github linkedin x

I study human cognition to code better.

# work.tex

Georgia State University
2025 - present Master’s of Science in Computer Science
  • 2025 - present Master’s of Science in Computer Science, Georgia State University, Atlanta, GA
Georgia State University
Graduate Teaching Assistant August 2025 - December 2025
  • Conducted bi-weekly office hours for 94 students, providing hands-on guidance and academic help.
  • Curated grading schemas for assignments, quizzes and exams.
  • Graded assignments, quizzes, and proctored exams, supporting the course instructor.
Ecommerce.co (Remote)
Senior Software Engineer May, 2025 - May, 2026
  • Developed an ecommerce marketplace SaaS using Typescript, Next.js, MongoDB, and GraphQL.
  • Built data pipelines for integration and management of complex Shopify workflows.
  • Optimized performance and query efficiency to scale to 10,000 active users/month.
  • Developed an AI Agent to intelligently understand natural language prompts and fetch products on the basis of extracted keywords.
Georgia State University
Graduate Teaching Assistant January, 2025 - May, 2025
  • Conducted weekly lab sessions, assisting 25 students per session.
  • Graded assignments, quizzes, and proctored lab exams, ensuring academic integrity.
WinningHunter (Remote)
Software Engineer October, 2023 - December, 2025
  • Developed and maintained SaaS platform features using PHP and JavaScript, building responsive UI components and RESTful API integrations while ensuring cross-browser compatibility and accessibility standards.
  • Implemented AI-driven features with strong focus on user experience (UX), digital content quality, and clear communication with non-technical, cross-functional stakeholders.
  • Built and deployed cron jobs and scheduled ETL processes for automated data ingestion, scheduled maintenance tasks, and database issue resolution.
  • Scaled platform to support 50,000 active monthly users and $2M+ in annual revenue through performance optimization and infrastructure improvements.
  • Increased platform reliability and user satisfaction through quality assurance, unit testing, troubleshooting, and iterative improvements on digital products.
Georgia State University
Graduate Research Assistant May 2025
  • Developed a multimodal AI-assisted clinical decision support system using large language models (LLMs) for multiple medical triage scenarios.
  • Applied retrieval-augmented generation (RAG) and task-specific fine-tuning with refined system prompts for GPT via the OpenAI API, achieving 95% F1 accuracy on medical NLP classification tasks.
  • Explored multimodal vision, speech, and text interaction in real time; evaluated model performance using precision, recall, and F1 metrics and analyzed human-AI dependency in medical decision-making.
Southeast Missouri State University
Graduate Research Assistant Sep 2024 - May 2025
  • Curated an open-source, validated dataset consisting of 400 peer reviews from journal articles, including data cleaning, annotation, and dataset documentation.
  • Fine-tuned LLMs (DistilBERT, RoBERTa, XLNet) for NLP peer-review text classification using supervised learning.
  • Achieved 76.71% validation accuracy with XLNet, optimized loss functions, and systematic hyperparameter tuning.
  • Evaluated comparative model performance using standard metrics (accuracy, precision, recall, F1), finding DistilBERT and XLNet outperformed others, while GPT-based models outperformed all BERT-based models.
Projects
Gradient Quantization for Federated Text Classification Feb 2026 - Apr 2026
  • Implemented adaptive gradient quantization for federated learning in text classification tasks to reduce communication overhead across edge devices.
  • Developed dynamic bit-width quantization (2-8 bits) for gradient compression in NLP models using PySyft and FedAvg algorithm.
  • Evaluated on sentiment analysis with DistilBERT across multiple client simulations, achieving 90%+ of full-precision accuracy.
  • Demonstrated significant communication reduction (8-16x bandwidth savings) while maintaining model performance in federated NLP settings.
Quantization-Aware Fuzzy Calibration for Edge LLMs Jan 2026 - Apr 2026
  • Developed novel fuzzy-gated Dirichlet calibration method for interpretable uncertainty quantification in transformer text classification.
  • Implemented cross-architecture calibration across 4 models (FinBERT, FinancialBERT, Gemma 3, Qwen 3.5) achieving 59-89% Expected Calibration Error (ECE) reduction.
  • Discovered counterintuitive finding that general financial training outperforms narrow task specialization by 5.56% accuracy.
  • Achieved optimal results with FinBERT: 60.08% accuracy, 0.033 ECE, 132 MB memory footprint suitable for edge deployment.
  • Paper in preparation for IEEE Machine Learning for Signal Processing (MLSP) 2026 conference.
Zero-Shot Classification for On-Device LLM Benchmarking
  • Developed an intelligent prompt routing system using zero-shot classification with a lightweight TinyLlama-1.1B-Chat model to select optimized quantized LLMs for each prompt category.
  • Implemented multi-model routing between specialized Qwen3-0.6B quantized models to enhance classification accuracy, efficiency, and generation quality across factual, reasoning, creative, instruction-heavy, and role-based tasks.
  • Designed a comprehensive benchmarking framework with curated prompts and performance metrics (energy consumption, memory usage, latency, throughput, accuracy).
  • Achieved more than 60% classification accuracy and demonstrated 15-30% performance improvement using auto-routing over single-model baselines, enabling efficient on-device execution with significant resource savings.
Vision Studio
  • Created a no-code computer vision platform with React/TypeScript for dataset labeling and model fine-tuning.
  • Enabled fine-tuning of ImageNet models using TensorFlow and automated annotation with YOLOv8.
  • Developed Django backend with PostgreSQL for efficient storage and retrieval.
Research Contribution
Published Work 2025

Aashir Aftab, Junaid Shuja et al. “Classifying Scientific Peer Reviews: Distinguishing Authentic, Generic, and AI-Generated Feedback.” Proc. 2025 IEEE International Conference on Future Machine Learning and Data Science (FMLDS 2025), Los Angeles, CA, USA, Nov. 2025

Published Work 2025

Aashir Aftab, Eyal Aharoni, Ttanvi Tummapudi. “AI-Assisted Medical Triage Training” Poster presented at the 2025 Innovations in Artificial Intelligence (AI) Conference, Little Rock, AR, USA, Oct. 2025.

Published Work 2026

Eyal Aharoni, Aashir Aftab, Ttanvi Tummapudi, Caelan Alexander-Nordstrom, Daniel Brady, Eddy Nahmias. “AI-Assisted Medical Triage: Mitigating Performance Errors in Human-AI Emergency Response Training.” Presentation, Proc. Human Factors and Ergonomics Society 2026 Annual Meeting, Baltimore, MD, USA, 2026.