Muhammad Anas Raza

Ph.D. Candidate & ML Systems / Research Engineer Β· Oakland University

prof_pic.jpg

Rochester, MI

Oakland University

🟒 Open to ML Systems & Research Roles

I am a Ph.D. Candidate in Computer Science & Informatics at Oakland University, specializing in Machine Learning Systems, Agentic AI, and Deep Learning Reliability.

My work bridges foundational deep learning with high-performance systems engineering, spanning zero-dependency C++/ggml inference engines, multi-backend ML libraries, autonomous multi-agent code generation, and multimodal computer vision forensics.

I am an active open-source contributor to core Keras 3 (20+ merged PRs) and author of timm.cpp (C++ inference engine for 106 vision models), K3Node (multi-backend GNNs with 100% PyG parity), and Keras-Climate.

12
Papers (7 First-Author)
237+
Citations (h-index: 5)
5+
Open-Source Projects

View All 12 Projects β†’
timm.cpp
C++17 / ggml

Standalone inference engine executing 106 PyTorch/timm architectures via GGUF with zero Python runtime dependency. Achieved up to 25.8Γ— faster cold-start load times via zero-copy POSIX mmap and 3.4Γ— to 5.8Γ— calibrated quantization weight compression.

K3Node & Keras 3
Core Contributor

Core contributor to Keras 3 with 20+ merged PRs. Author of K3Node (multi-backend GNN library with 100% PyG parity across PyTorch, TensorFlow, and JAX with 700+ tests/backend), K3IM (50+ vision backbones), and Keras-Climate.

AutoMAS & NeuroGenesis
IEEE QRS 2026

Architected AutoMAS, an autonomous framework translating natural language code intent into working multi-agent systems across 5 cooperative layers (82.75% Pass@1). Authored NeuroGenesis, introducing reasoning-guided multimodal architecture search using LLMs.

DL Reliability & Forensics
Best Poster Award

Authored RuleBoost (Best Poster Award at IEEE IJCB 2024; 96.19% AUC), LocatorGraph (Empirical Software Engineering 2025; GNN fault localization on DL computation graphs), and DeepTrAnS (IEEE ICSC 2025; 99.88% precision telemetry anomaly detection).


Technical Expertise & Skills

Programming Languages
Python C++ / C++17 TypeScript JavaScript (ES6+) CUDA Dart Rust (basics) Bash SQL LaTeX
Deep Learning Frameworks
PyTorch Keras 3 TensorFlow JAX LibTorch timm Hugging Face LangGraph scikit-learn NumPy & pandas
ML Systems & Inference Engineering
ggml & GGUF llama.cpp / llama-server Zero-Copy POSIX mmap Calibrated Quantization (Q8_0, Q4_0, Q4_K) Weight Porting Pipelines Numerical Parity Testing AVX-512 / ARM NEON SIMD
Cloud, MLOps & Infrastructure
AWS (S3, EC2, Lambda, SageMaker, VPC, IAM, EKS) Docker & Docker Compose Kubernetes (kubeadm, kubectl, AKS, GKE) Terraform (IaC) HPC / SLURM Tesla V100 Clusters NVIDIA Jetson Edge InfluxDB & Grafana
Full-Stack Platforms
React 19 & Vite React Native & Expo SDK 53 Flutter & Dart Node.js & Express Apollo Server & Client GraphQL Subscriptions (WebSockets) MongoDB & Aggregations Tailwind CSS v4

Recent Milestones & News

View All Publications β†’
  • 2026: Two research papers accepted at IEEE QRS 2026: AutoMAS (End-to-End Generation of Functional Multi-Agent Systems) and NeuroGenesis (LLM-Driven Neural Architecture Search).
  • 2026: Released Keras-Climate, a multi-backend framework for Earth Observation and Climate Modeling.
  • 2025: Published Graph Neural Network for Fault Localization in Sequence-Based Models (LocatorGraph) in Empirical Software Engineering (EMSE).
  • 2025: Published DeepTrAnS: Mixer-based Unsupervised Time Series Anomaly Detection for Servers in IEEE ICSC 2025.
  • 2024: Received the Best Poster Award at IEEE IJCB 2024 for RuleBoost: A Neuro-Symbolic Framework for Robust Deepfake Detection.

selected publications

  1. AutoMAS: End-to-End Generation of Functional Multi-Agent Systems
    Muhammad Anas Raza, Niful Islam, and Mohammad Wardat
    In IEEE International Conference on Software Quality, Reliability and Security (QRS), 2026
  2. Graph neural network for fault localization in sequence-based models
    Muhammad Anas Raza and Mohammad Wardat
    Empirical Software Engineering, 2025
  3. RuleBoost: A Neuro-Symbolic Framework for Robust Deepfake Detection
    Muhammad Anas Raza, Khalid Mahmood Malik, and Ijaz Ul Haq
    In 2024 IEEE International Joint Conference on Biometrics (IJCB), 2024
  4. Multimodaltrace: Deepfake detection using audiovisual representation learning
    Muhammad Anas Raza and Khalid Mahmood Malik
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023