CV

This is the curriculum vitae of Mohammed Musthafa Rafi.

General Information

Education

August 2023 - Present
Ph.D. Candidate in Computer Science
Iowa State University, Iowa, USA
  • GPA: 3.91/4.00
August 2023 - May 2026
Master of Science in Artificial Intelligence
Iowa State University, Iowa, USA
  • GPA: 3.93/4.00
  • Thesis: Benchmarking Tabular Foundation Models for Agricultural Yield Prediction
July 2018 - July 2022
Bachelor of Science in Electrical and Electronics Engineering
APJ Abdul Kalam Technological University, Kerala, INDIA
  • July 2018 – July 2022

Experience

2023 - Present
Graduate Teaching Assistant
Iowa State University
  • COM S 309 (Software Development Practices)
    Spring 2023, Fall 2024
    Guided and mentored 8 student teams with 4–5 members each, helping them with software-development practices and collaborative project work.
    Held lab sessions, assisted students with coding and debugging, and supported their use of tools like GitHub for project management.
  • COM S 336 (Computer Graphics)
    Fall 2023
    Prepared quizzes on TopHat, conducted office hours, and provided student support via Piazza discussions
    Conducted labs focused on teaching 3-D rendering, visualization techniques, and basic graphics programming

Research / Internship

August 2024 - Present
Research
Iowa State University, Ames, IA
  • Slice 100k work
    To generate cad designs from code prompts
  • NeRF pipeline (non-standard turntable capture)
    Built a Neural Radiance Field pipeline for a stationary-camera, rotating-object setup: custom camera pose estimation and view synthesis, trained and evaluated on ISU HPC with multi-GPU acceleration. Extended with NeRF-SOS for self-supervised object segmentation—achieving <2° reprojection error from 150 fixed-camera images, collaborative contrastive loss for zero-annotation 3D segmentation (15% IoU gain over supervised baselines), and SAM2-based masking (≈30% faster training), producing watertight meshes and per-object neural fields for CAD/robotics.
  • TabPFN for Time-Series Forecasting on Industrial IoT
    Deployed the TabPFN foundation model on multivariate sensor streams across 1,300+ hierarchical units (68,200+ observations). Achieved state-of-the-art R² of 0.881 and RMSE of 7.1, outperforming traditional ML while reducing training time by ~100×. Demonstrated foundation model evaluation, benchmarking, and custom PyTorch training loops with gradient checkpointing; production stack included sliding-window inference, calibration, drift monitoring, and deployment-focused monitoring for robust performance.
  • Distributed ML/LLM workflows on HPC
    Developed distributed training and inference workflows on university HPC (SLURM, Nova): multi-node GPU jobs, parallel data preprocessing, and reproducible experiment tracking with MLflow and Weights & Biases across 1000+ concurrent tasks.
  • Agentic Retrieval-Augmented Text2CAD System (OpenSCAD)
    • Architected a fully traceable multi-agent LLM pipeline using LangGraph for stateful orchestration—conditional execution paths, inter-agent communication protocols, and hierarchical task decomposition across six specialized agents (Reasoner, Planner, Compiler, Verifier, Repair, Assembler)—with structured logging at each agent decision point, producing parametric OpenSCAD from natural language.
    • Integrated retrieval-augmented generation with GPT-5: FAISS vector search over 500+ domain artifacts (Fusion360 Gallery reconstructions and related assets) using L2-normalized embeddings, hybrid retrieval over meshes (OBJ/STEP/SMT) and synthetic CAD sequences; ~40% latency reduction via intelligent caching; built systematic evaluation pipelines for multi-agent reasoning quality. Achieved 75% semantic accuracy through sequence-based sketch–extrude–boolean construction.
    • Designed agent-level reward mechanisms through iterative self-repair validation: system-level compilation and verification signals propagate back to individual agents for targeted correction, improving task success via post-training refinement strategies—including OpenSCAD compilation success from 68% to 89%—while improving schema pass rate from 73% to 94%, maintaining 91% parametric dependency preservation and correct spatial reasoning for placement and clearances.
    • Implemented credit assignment for the multi-agent stack: fine-grained feedback from global task outcomes to individual agent actions; 40% reduction in cascading failures through localized error attribution and controlled ablation experiments.
    • Developed hierarchical assembly decomposition (Block → Parametric → Full Model). Validated on complex furniture and mechanical assemblies (tables, chairs, components) with 1000+ line JSON IR generation.

Publications

  • M. M. Rafi*, T. Ayanlade, B. Ganapathysubramanian, S. Sarkar, A. Krishnamurthy, C. Hegde, A. Balu: "Benchmarking Tabular Foundation Models for Agricultural Yield Prediction", AgriAI 2026 Workshop, AAAI 2026. [article]
  • M. M. Rafi*, A. Krishnamurthy, A. Balu, et al.: "Trustworthy LLM-Mediated Communication: Evaluating Information Fidelity in LLM as a Communicator (LAAC) Framework in Multiple Application Domains", IEEE DISTILL, 2025. [article]

Technical Skills

Programming Languages

  • Python, C++, CUDA, JavaScript, MATLAB, R

Machine Learning & AI

  • PyTorch, TensorFlow, scikit-learn, Keras, OpenCV, Transformers, Diffusion Models

High-Performance Computing

  • CUDA, MPI, OpenMP, GPU Computing, HPC Cluster Management

CAD & Engineering Software

  • SolidWorks, ANSYS, FEA, CFD

Data Analysis & Visualization

  • Pandas, NumPy, Matplotlib, Plotly, Paraview, VTK

Projects

Prompt-to-Perception: Integrated Text-to-Image Pipeline

  • Developed an end-to-end system for text-to-image generation using prompt refinement and Stable Diffusion 2.1.
  • Improved prompt quality 3× (ROUGE metrics) via T5-Small, with an average prompt-image alignment of 0.72.
  • Code | Demo Video | Document

TraitViz – Interactive PubMed Annotation Visualizer

  • Built a full-stack web app for automatic annotation and visualization of PubMed articles with entity extraction and SVG parse graphs.
  • Code | Video | Document

CNN Visualization

  • Built an interactive system to inspect intermediate layers of CNNs. Given an input image, it renders per‑layer activation maps and optionally visualizes filter weights. Added forward hooks and epoch snapshots to step through training for real‑time introspection and debugging
  • Code| Video | Document

Diseased Plant Detection

  • Created ResNet50, VGG16, and custom CNNs for new plant disease detection across 38 vision classes.
  • Document

Certifications & Awards

Certifications

  • Fundamentals of Accelerated Computing with CUDA C/C++ (NVIDIA)
  • Complete Python With DSA Bootcamp by Krish Naik, Udemy (In progress)
  • Complete Machine Learning, NLP Bootcamp with MLOps and Deployment by Krish Naik, Udemy (In progress)
  • Neural Radiance Fields & Implicit Neural Representations (Digital Badge, May 2025, TrAC, ISU)
  • MLOps: Machine Learning in Practice (Digital Badge, Nov 2024, Translational AI Center, ISU)

Awards

  • Winner, Applied AI Challenge 2026: AI-Assisted Making Award, for Study Buddy - an AI-powered learning companion built with AI-assisted development tools
    Certificate
  • Constellation Prize (Top 4/30+ teams), Ivy Data Visualization & Storytelling Case Competition, Ivy College of Business
  • Winner, Applied AI Challenge 2025: Karma AI – Social Impact Award ($1500), for an AI solution empowering the visually impaired using multimodal prompting and GPT-based voice assistant
    Code | Demo
  • 2nd Place, Fall 2023 Coding Contest, CSE Programming Club

Contact