# Ali Salloum — English site copy for LLMs This document is generated from the live translation file (`messages/en.json`), blog posts (`content/blog`), and public site config. It is served at `/llms.txt` for tools and automation (e.g. cold outreach drafting). ### Canonical URLs (English) - Home: https://www.alisalloum.tech/en/ - Services: https://www.alisalloum.tech/en/services - Portfolio: https://www.alisalloum.tech/en/portfolio - About: https://www.alisalloum.tech/en/about - Contact: https://www.alisalloum.tech/en/contact - Blog index: https://www.alisalloum.tech/en/blog --- ## Metadata - **siteName:** Ali Salloum - **defaultTitle:** Ali Salloum | AI-Accelerated Full-Stack Architect - **defaultDescription:** Building scalable software with AI-accelerated speed. Backend, full-stack web, Flutter, and AI/ML integration — production-ready architecture. ## Navigation labels - **home:** Home - **services:** Services - **portfolio:** Portfolio - **about:** About - **blog:** Blog - **contact:** Contact - **startProject:** Start a Project ## Footer - **tagline:** Ali Salloum — Full-Stack Architect - **response:** Typical response: < 12 hours - **copyright:** © 2026 Ali Salloum. Moscow UTC+3. ## Contact (human-facing) - **Let's talk** Tell me about your product, timeline, and constraints. I reply within 12 hours (Moscow UTC+3). - **Prefer direct contact?** Email: ali.e.salloum@gmail.com - **Telegram:** https://t.me/ali0006e Other profiles (as configured on the site): GitHub https://github.com/ali-salloum6, LinkedIn https://linkedin.com/in/ali-salloum ## Home - **badge:** Available for Partnerships - **title:** Ali Salloum - **tagline:** Building scalable software with AI-accelerated speed. Full-Stack Architect specialized in accelerated delivery. - **ctaPrimary:** Start a Project - **ctaSecondary:** View Portfolio - **equationTitle:** The Delivery Equation - **equationTotal:** Total Value - **equationKnowledge:** Deep Knowledge - **equationMultiplier:** AI Multiplier - **equationCaption:** Leveraging generative AI as a force multiplier to ship high-fidelity architectures in record time without compromising on system integrity. - **servicesTitle:** Service Highlights - **servicesSubtitle:** Architectural expertise meets AI speed. - **viewAllServices:** View All Services - **serviceBackendTitle:** Robust Backend - **serviceBackendDesc:** Distributed systems and microservices designed for 99.9% uptime and extreme scale. - **serviceFullstackTitle:** Full-Stack Craft - **serviceFullstackDesc:** End-to-end product development with polished UI/UX and seamless state management. - **serviceMobileTitle:** Mobile - **serviceMobileDesc:** Cross-platform apps with native feel or actual native apps, solid offline strategy, and backend integration. - **serviceAiTitle:** AI & ML Integration - **serviceAiDesc:** Embedding LLMs and predictive models into your workflows for automated value. - **learnMore:** Learn More - **portfolioTitle:** Selected work - **case1Tag:** Infrastructure • Case Study 01 - **case1Title:** Unified Manager for Multi-Agent Deployment - **case1Desc:** One manager per environment and automated agent provisioning from the admin UI—repeatable deploy without manual per-agent plumbing. - **case2Tag:** Frontend • Case Study 04 - **case2Title:** LuukAI — Embeddable AI Assistant & Partner Widget - **case2Desc:** Conversational Q&A, recommendations, and a floating embed—multilingual, on-brand per tenant, one React/TypeScript pipeline. - **statsYears:** Years Exp - **statsYearsValue:** 9+ - **statsDegree:** CS Degree - **statsProjects:** Projects Shipped - **statsProjectsValue:** 50+ - **statsMl:** ML Certified - **bottomCtaTitle:** Ready to build the future? - **bottomCtaBody:** Whether you need a fractional CTO or a full-stack execution partner, let's discuss how AI-accelerated development can scale your product. - **bottomCtaPrimary:** Start a Project - **bottomCtaSecondary:** Book a Call ## Services - **metaTitle:** Services - **metaDescription:** Backend, full-stack web, Flutter mobile, and AI/ML integration — timelines, pricing guidance, and how we work. - **heroBadge:** Available for new projects - **heroTitle:** AI-Accelerated Architectural Excellence - **heroSubtitle:** High-performance engineering for the next generation of digital products — from deep backend systems to intelligent mobile experiences. - **trustTimezoneTitle:** Timezone Reliable - **trustTimezoneBody:** Moscow UTC+3 — overlap with Europe & MENA. - **trustResponseTitle:** Rapid Response - **trustResponseBody:** Replies within < 12 hours for any inquiries. - **pricingTitle:** Pricing guidance - **pricingBody:** Discovery calls are free. Typical engagements start around $1k. Most product builds fall in the $5k–$10k range depending on scope, SLA, and timeline. Fixed quotes after architecture review. - **howTitle:** How I work - **howStep1:** Discovery - **howStep2:** Proposal - **howStep3:** Architecture - **howStep4:** Development - **howStep5:** Delivery - **s1Time:** 1–2 weeks - **s1Title:** Backend & API Development - **s1Desc:** REST/GraphQL, database design, microservices, and high-concurrency infrastructure. - **s1Cta:** Discuss this project - **s2Time:** 2–4 weeks - **s2Title:** Mobile App Development - **s2Desc:** Cross-platform apps for iOS and Android with backend integration and offline-first patterns where needed. - **s2Cta:** Discuss this project - **s3Time:** 6-8 weeks - **s3Title:** Full-Stack Web Applications - **s3Desc:** SaaS, admin dashboards, and complete web products from UI to production deployment. - **s3Cta:** Discuss this project - **s4Time:** 4-8 weeks - **s4Title:** AI/ML Integration & Automation - **s4Desc:** LLM integration, RAG, chatbots, and data pipelines — production-hardened, not demos. - **s4Cta:** Discuss this project - **closingTitle:** Ready to architect your vision? - **closingBody:** Schedule a free 30-minute technical discovery call to discuss architecture and roadmap. - **closingPrimary:** Book Discovery Call - **closingSecondary:** View Portfolio ## Portfolio — hero & philosophy - **metaTitle:** Portfolio - **metaDescription:** Anonymized case studies: architecture, scale, and how problems were solved — NDA-safe highlights. - **heroTitle:** Ali Salloum - **heroSubtitle:** AI-Accelerated Full-Stack Architect — scalability, security, and production-readiness. - **philosophyTitle:** Core Architecture Philosophy - **p1Title:** Performance-First - **p1Body:** P99 latency is a requirement. Compute is optimized for cost and speed. - **p2Title:** Security by Design - **p2Body:** Security in schema, network topology, and CI/CD — not bolted on at the end. - **p3Title:** Infinite Scalability - **p3Body:** Stateless services and distributed state from ten users to ten million. - **ctaTitle:** Ready to scale your vision? - **ctaBody:** Let's discuss production-ready architecture for your performance and security needs. - **ctaPrimary:** Schedule a Consultation - **ctaSecondary:** Contact ## Portfolio — case studies ### c1 - **tag:** CI/CD • Case Study 01 - **title:** Legacy Deployment Modernization - **body:** I inherited a brittle deployment setup with per-agent manual steps, scattered config edits, and high maintenance overhead. I consolidated it into a predictable release flow with one control surface per environment, automated routine operations from the admin UI, and safer rollouts that reduced operator friction and recovery time. - **m1:** 25 → 1 - **m1l:** Services to Manage - **m2:** < 5ms - **m2l:** Proxy Overhead - **f1:** Replaced repetitive manual deployment steps with a consistent, operator-friendly workflow. - **f2:** Made backups and multi-server rollout simpler and less error-prone through standardized service layout. - **imageAlt:** Blueprint diagram: reverse proxy to Manager, then routing to Unix sockets for supervisor and agents ### c2 - **tag:** Backend • Case Study 02 - **title:** Admin Campaign Orchestration on PocketBase - **body:** I built a notification orchestration subsystem on top of the app's PocketBase backend so non-technical admins can launch targeted campaigns without engineering help. The system handles audience selection, queued delivery through Firebase, real-time progress tracking, and full delivery telemetry so teams can see exactly what was sent, what failed, and what needs retry. - **techTitle:** Technical focus - **f1:** Designed a deterministic queue worker with per-device status transitions, retries, and idempotent processing to prevent duplicate sends. - **f2:** Added an admin-facing control and observability layer: campaign states, delivery logs, completion guarantees, and failure diagnostics. ### c3 - **tag:** Web Scraping / Automation • Case Study 03 - **title:** Partner Onboarding Data Engine for AI Q&A - **body:** I built this ingestion engine to accelerate partner onboarding at scale: crawl a partner domain, normalize products and content into structured records, and feed them directly into the AI Q&A system. Instead of hand-crafting parsers per site, one adaptive pipeline handles storefronts, blogs, and mixed structures, which dramatically reduced time-to-integration and increased the platform's commercial value. - **arch:** Business impact - **archVal:** Faster partner onboarding and time-to-value - **archVal2:** Structured data pipeline powering production AI Q&A - **metric:** 97% - **metricLabel:** Audited field accuracy ### c4 - **imageAlt:** LuukAI promotional popup with branded header, headline, and action buttons - **demoLink:** Live widget demo - **tag:** Frontend • Case Study 04 - **title:** LuukAI — Embeddable AI Assistant & Partner Widget - **body:** Partners drop in a conversational assistant: plain-language Q&A, smart recommendations, optional promos, and guided flows when needed. One codebase ships as a full web app and a floating embed—on-brand per tenant, multilingual, and built so the host site’s styling can’t break the experience. - **techTitle:** Built with - **techVal:** React · TypeScript · Vite — one pipeline, multiple surfaces (app, widget, embedded shell) - **engineeringTitle:** Highlights - **f1:** The widget is visually self-contained—partner pages don’t accidentally restyle or break the assistant. - **f2:** Surveys, partner add-ons, and analytics hook in cleanly so journeys feel native, not bolted on. - **f3:** Per-brand copy, languages (including RTL), and tailored result screens—down to industry flows and booking handoff to the host. ### c5 - **tag:** Publication • Case Study 05 - **title:** Quantum annealing in machine learning: Qboost on D-Wave quantum annealer - **body:** Peer-reviewed paper on quantum annealing and machine learning: a QBoost-style ensemble mapped to a quadratic unconstrained binary optimization (QUBO) formulation and run on a D-Wave quantum annealer. It explores when quantum hardware can complement classical ML pipelines, how experiments are set up on real hardware, and how to read results within device constraints. - **venueTitle:** Venue - **venueVal:** Procedia Computer Science (Elsevier), 2024 - **citationBlockTitle:** Scholar impact - **citationFallbackCount:** 12 - **citationRest:** citations on Google Scholar - **paperLink:** Paper (ScienceDirect) - **scholarLink:** Citing articles (Google Scholar) - **natureLink:** Recent citation: npj Computational Materials (Nature Portfolio) — materials discovery using quantum-annealed ML - **engineeringTitle:** Highlights - **f1:** Connects quantum annealing with ML: QBoost framing executed on D-Wave hardware with a clear experimental narrative. - **f2:** Sits at the intersection of QC and ML—relevant as both fields converge in research and applied work. - **f3:** Growing citation footprint, including follow-on work in Nature Portfolio journals (e.g. npj Computational Materials). ### c6 - **imageAlt:** Week of electricity price data: truth (blue line) vs model prediction (orange points), Dec 24–29, 2023 - **pdfLink:** Full report (PDF) - **tag:** ML / Forecasting • Case Study 06 - **title:** Decision-Grade Electricity Price Forecasting - **body:** I built this forecasting system as a practical decision-support tool: it turns historical market signals into forward-looking price estimates that can inform planning, procurement timing, and risk controls. The pipeline covers data conditioning, supervised model training, and rigorous holdout evaluation, then exposes forecast behavior clearly so teams can act on trend direction and peak windows. - **evalTitle:** Operational takeaway - **evalVal:** The model captures recurring intraday structure and turning points with useful accuracy for planning and timing decisions. - **engineeringTitle:** Highlights - **f1:** Production-oriented evaluation slice: actual vs forecast on the same dense timeline for fast operator interpretation. - **f2:** Captures strong cyclical price behavior and timing shifts instead of relying on naive baselines. - **f3:** Evaluation outputs are decision-ready and easy to operationalize in planning workflows. ### c7 - **tag:** AI • Case Study 07 - **title:** Agent Coach — long-memory Telegram assistant - **body:** A production Telegram bot where memory is a first class feature: goals and facts accumulate in simple files, load into every new chat, and improve after each reply. One codebase powers multiple specialist bots—same polished command surface, different expertise. Under the hood: Python with one-tap quality presets, optional live web lookup, and a backup model when traffic spikes so the chat keeps moving. - **detailTitle:** Model presets - **detailVal:** Lean · balanced · max quality - **highlightsTitle:** Highlights - **f1:** Session threads reset; long-term context does not—so coaching stays personal across weeks. - **f2:** Shipped examples include fitness coaching and German exam prep; swap persona per deployment. ## About - **metaTitle:** About - **metaDescription:** From competitive programming to AI-augmented full-stack delivery — background, credentials, and how I work with LLMs. - **heroTitle:** Ali Salloum - **heroSubtitle:** AI-Accelerated Full-Stack Architect. Bridging conceptual complexity and production-ready systems at speed. - **chip1:** Rapid Delivery - **chip2:** AI-First Workflow - **journeyTitle:** The Narrative Journey - **j1Title:** The Genesis: 2017 - **j1Body:** Competitive programming forged algorithmic discipline — performance and correctness still drive my architecture choices. - **j2Title:** Academic Rigor - **j2Body:** Earlier in my journey, I ranked 15th nationwide with 99.98% in my final high-school exams (verify results). My Computer Science degree included software design, computer architecture, and the engineering principles behind reliable systems. I'm currently pursuing a master's in AI. - **j3Title:** Web3 & Flutter - **j3Body:** Worked on decentralized systems and cross-platform apps for complex domains. - **j4Title:** Full-Stack Systems Engineer (AI-Augmented) - **j4Body:** Today: advanced AI workflows multiply output while architecture stays scalable, secure, and production-grade. - **certsTitle:** Machine Learning & AI Credentials - **certsBadge:** Coursera & more - **cert1Issuer:** Stanford Online - **cert1Name:** Machine Learning Specialization - **cert2Issuer:** DeepLearning.AI - **cert2Name:** Neural Networks and Deep Learning - **cert3Issuer:** DeepLearning.AI - **cert3Name:** Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization - **cert4Issuer:** ICPC - **cert4Name:** Competitive programming certificates - **philosophyTitle:** The AI-Augmented Advantage - **philosophyBody:** Production quality without sacrificing speed. LLM-assisted delivery, automated tests, and AI-assisted review — robust architectures in days, not months. - **pillar1:** 10x Velocity - **pillar2:** Clean Output - **pillar3:** Robust Core ## Blog — section metadata - **metaTitle:** Blog - **metaDescription:** Notes on architecture, AI-assisted delivery, and shipping reliable software. - **title:** Blog - **subtitle:** (empty) ## Blog — posts (full MDX body, English) ### building-this-portfolio ```yaml title: Building this portfolio with Stitch and Cursor date: Tue Mar 24 description: the power of AI ``` ## How I built this This site took me 30 minutes to build with no boilerplates and completely customizable with exactly what I wanted to include. --- _End of export._