ENGINEERING AT THE
DATA × AI INTERSECTION.
I am Anuj Mundu, an AI/ML Engineer, Data Scientist, and Python Backend Architect who turns ambiguous data and theoretical machine learning architectures into resilient, low-latency production systems.
Graduating with a Master of Computer Applications (MCA) from the prestigious Maulana Azad National Institute of Technology (MANIT Bhopal), I reject the divide between data analysis and software engineering. Every system I architect unites rigorous statistical validation, strict Pydantic contracts, asynchronous Celery worker meshes, and containerized Kubernetes Helm deployments.
STRESS TEST THE ARCHITECTURE IN REAL TIME
01 // APPLIED DEEP LEARNING & DSP
FLAGSHIP EVIDENCE: PulmoScan CADx SuiteBridges deep tensor inference with dark-mode clinical radiologist HUDs, sub-40ms bounding box rendering, and Grad-CAM explainability overlays.
FIRST-PRINCIPLES MINDSET & REALITY CHECK
Respect the Raw Data
No model outperforms bad data. We invest 70% of engineering effort in rigorous cleaning, temporal integrity, and domain-informed feature transformations before touching neural weights.
Occam's Razor in Modeling
Start with strong, interpretable statistical baselines. Only introduce deep neural architectures when the complexity genuinely yields measurable, non-marginal real-world gains.
Code Beyond the Notebook
A model trapped in a Jupyter notebook is an experiment, not a system. Production excellence means low latency, strict API contracts, Docker isolation, and deterministic failure recovery.
Explainability is Non-Negotiable
Stakeholders and operators cannot trust what they cannot inspect. Every predictive decision should be accompanied by calibrated confidence intervals and attribution vectors.
PRODUCTION TOOLING & RUNTIME STACK
Click on any technology chip below to inspect its production application role and verification metrics.
Applied AI & Computer Vision
Distributed Backends & MLOps
Data Science & Explainable AI
Data Engineering & Storage
INSTITUTIONAL & SYSTEMS TRAJECTORY
Python Backend & AI/ML Systems Engineer
- Architected production multimodal platforms (OmniForge) integrating Agentic RAG, neural vision, Celery-Redis distributed queues, and Kubernetes Helm deployments.
- Engineered clinical CADx suites (YOLOv5-CASP) with CBAM attention, ASPP context, and CoT3 transformers for automated pulmonary nodule localization.
- Built production workforce MLOps platforms (RetainAI) using FastAPI, PyTorch Tabular ResNet/VAE, TreeSHAP explainability, and Kolmogorov-Smirnov statistical drift detection.
- Developed high-reliability distributed task engines with decoupled worker daemons, Redis queues, and durable PostgreSQL state machines.
Master of Computer Applications (MCA)
- Premier National Institute of Technology (NIT) curriculum covering Advanced Data Structures & Algorithms, Distributed Systems, Cloud Computing, Database Management Systems, Machine Learning, and Computer Vision.
- Authored research and engineering projects on Automated Multi-Modal Lung Nodule Detection using YOLOv5-CASP with attention mechanisms and real-time medical imaging workstations.
- Engineered end-to-end full-stack AI/ML systems including distributed worker queues, agentic reasoning microservices, and statistical diagnostic pipelines.
Bachelor of Science (Honours) in Computer Science
- Graduated with First-Class Honours with core focus on Computer Science fundamentals, Object-Oriented Programming, Discrete Mathematics, and Relational Databases.
- Developed foundational algorithmic problem-solving capabilities, database schema design, and Linux systems administration.
- Implemented statistical data analysis, scientific computation, and machine learning models for academic research projects.
READY TO ARCHITECT RESILIENT INTELLIGENCE?
Whether it's scaling a distributed inference worker mesh, structuring high-throughput SQL analytics, or training medical computer vision models, I am available for high-impact engineering roles.