Murad Al-Balushi
Applied AI Engineer & Full-Stack Developer
Building production AI systems and scalable full-stack applications. I design and ship intelligent solutions end-to-end—from RAG engines to fintech platforms—combining AI capabilities with robust architecture to deliver measurable impact.
Professional Experience
Real-world impact and teamwork in production environments
360Remit
Software Developer
Muscat, Oman
Jan 2024 – Present
At 360Remit, I helped build the backend from nearly the ground up, designing it to be scalable for future growth. My work spanned architecture, automation, and integrations that enabled the product to scale reliably and safely in a regulated fintech environment.
- Backend architecture: Helped build the backend infrastructure from nearly the ground up, designed for scalability and future growth
- Risk analysis system: Developed a real-time risk and compliance engine to evaluate users and beneficiaries, strengthening onboarding security and fraud prevention
- Automation: Built end-to-end Python pipeline for live data synchronization between external API and our database, eliminating manual data uploading and improving data consistency — saving 5+ hours per week in manual operations
- Infrastructure: Greenfield infrastructure setup from requirements consolidation to vendor coordination, working as point of contact with local providers
- Compliance foundation: Proposed and implemented the initial KYC flow that underpins customer verification across the platform
- Integrations: Led integrations with eKYC services, identity verification APIs, and MTO payment gateway, connecting external APIs into a unified transaction ecosystem
Engineering Village
Development Intern
Al Mawaleh
May 2024 – Aug 2024
- Built a booking app using React and Supabase with real-time conflict resolution, eliminating double-bookings
- Developed reusable component abstractions for scalable UI system design, reducing development time
- Delivered production-ready features in a collaborative, learning-focused environment
Technical Skills
Core technologies I use to build scalable, modern applications
Frontend
- React, Next.js 15
- TypeScript/JavaScript
- Tailwind CSS
- Responsive Design
- Modern UI/UX Patterns
Backend
- Python (FastAPI, AI/ML)
- Automation Scripting (Python)
- FastAPI + Next.js Integration
- Node.js, Express
- REST APIs & third-party API integration
- MongoDB, PostgreSQL, SQLite
- Authentication & Security (JWT)
- File Processing (PDF, DOCX, TXT)
AI/ML
- LLM Integration (OpenAI API, GPT-4)
- Vector Databases & Semantic Search (FAISS)
- RAG Architecture & Context Retrieval
- Intelligent Memory Systems
- Hybrid Retrieval (Semantic + Lexical + RRF)
- Confidence Scoring Systems
- Text Embeddings (tiktoken + OpenAI)
- Document Processing & Chunking
- Speech Recognition (Whisper)
DevOps / Cloud
- Docker & Docker Compose
- AWS (EC2, S3, ECS – basic)
- GitHub Actions (CI/CD)
- Nginx Web Server
- Vercel (frontend deployment)
- Container Orchestration
Other
- Testing (Jest)
- Documentation & Technical Writing
- System Design & Architecture
- spaCy Preprocessing
- BM25 Search
- Reciprocal Rank Fusion
- Agile Development / Collaboration
Featured Projects
Real-world applications that solve business problems and demonstrate technical expertise
Cortex
An applied-AI system that enables semantic understanding and querying across multi-format documents. Reduces document analysis time from hours to minutes with 95%+ accuracy.
Problem
Organizations struggle to extract insights from large document collections. Traditional search methods fail to understand semantic meaning, and manual document analysis is time-consuming and inconsistent.
Solution
A production-ready Retrieval Augmented Generation system featuring an Intelligent Memory System for context-aware sessions, Hybrid Retrieval (Semantic + Lexical + RRF), and Confidence Scoring with source attribution. Built with FastAPI, Next.js, and OpenAI's latest models.
Containerized and deployed on AWS for scalable access and reproducible testing.
Tech Stack
Key Features
- Intelligent Memory System for context-aware sessions and conversation history
- Hybrid Retrieval combining Semantic Search, BM25 Lexical Search, and Reciprocal Rank Fusion
- Confidence Scoring with source attribution and visual confidence badges
- Multi-format document pipeline (PDF/DOCX/TXT) with session-based metadata
- Modular LLM integration supporting multiple models and providers
- Vector similarity search using FAISS for semantic document retrieval
- Containerized deployment with Docker Compose and Nginx
- Responsive web interface with modern UX patterns
Backend not deployed to cloud at the moment (previously hosted on Railway). Demo accessible through screenshots.
Fenzo - Business Management Platform
A comprehensive SaaS platform that automates the entire client-to-invoice workflow for freelancers and agencies. Reduces administrative workload by 60%+ and eliminates billing errors.
Problem
Freelancers and agencies struggle with managing quotes, invoices, and projects in one place.
Solution
A full-stack SaaS platform for freelancers/agencies. Features dynamic quotation workflows, project tracking, automated invoicing, and secure client portals. Built with React, Node.js, PostgreSQL, and JWT auth, Fenzo automates the entire client → project → invoice pipeline.
Tech Stack
Key Features
- Dynamic quotation workflows with real-time calculations
- Project tracking with milestone management
- Automated invoice generation with PDF export
- Secure client portals with role-based access
- Time tracking with billable/non-billable hours
Summit – AI Learning Accelerator
A desktop AI application that transforms audio content into structured learning materials and flashcards. Saves 3-5 hours per lecture in note-taking and improves retention with spaced repetition.
Problem
Learners and professionals forget most of what they hear in lectures, courses, or meetings. Manually taking notes wastes attention, and reviewing raw transcripts is overwhelming.
Solution
Summit automatically records system audio, transcribes it with Whisper, summarizes with GPT, and generates flashcards for Obsidian/Anki.
Tech Stack
Key Features
- Record system audio
- Runs Whisper locally for privacy (GPU recommended)
- Structured summaries per chunk + master summary
- Quick or deep flashcards for retention
- Minimalistic desktop app (PySide6)
- Packaged as a standalone Windows .exe for frictionless use
Remotable - Job Aggregator
An intelligent job aggregation system that delivers personalized remote job alerts via Discord webhooks. Automated pipeline processes 1,300+ job postings daily from multiple sources.
Problem
Job seekers need to check multiple job boards daily to find relevant remote opportunities.
Solution
Remotable aggregates remote jobs from multiple sources and delivers personalized alerts via Discord webhooks.
Tech Stack
Key Features
- Job aggregation from multiple remote job APIs
- Daily automated job collection and processing
- Discord webhook integration for notifications
- User-friendly setup without account creation
Let's Connect
Ready to discuss your next project or explore opportunities? Reach out through any of these channels.