Computer Engineering student and Interviewlary co-founder building applied-AI and full-stack systems across LLM infrastructure, voice AI, agent workflows, and production web products. Strongest in product definition, integration, debugging, testing, and evidence-based release QA.
Co-founded and helped ship a live AI interview-training SaaS with role-specific question generation, bilingual voice/text mock interviews, transcription, scoring, feedback, subscriptions, and performance history.
Lead product requirements, provider evaluation, technical QA, and release review across LLM generation, STT/TTS, authentication, billing, scoring, feedback, latency, and failure-path behavior.
Contribute to implementation and debugging through repository inspection, logs and Sentry, integration work, journey testing, and edge-case verification; translate product failures into scoped engineering fixes.
Technical projects & systems
Examina AI (Digital SAT)
Shipped · Staging
Comprehensive Digital SAT prep platform featuring a Socratic AI tutor (server/tutor.ts) designed to guide students without answer leakage, dynamic difficulty modules, interactive knowledge maps, Three.js 3D mascot, and Playwright cross-browser test suites.
TokensCache
Shipped · Open Source
TypeScript and Node multi-provider LLM optimization layer with exact and semantic caching, prompt optimization, provider adapters, real-dollar budget controls, and MCP tooling. 92/92 tests passing; 35.5% fewer billed tokens in repository mock A/B scenarios.
TruthNet
Award Winner · AI Hackathon
FastAPI and React real-time fact-checking system using a four-agent adversarial pipeline (Research, Prosecution, Defense, Judge) for evidence gathering and final credibility scoring. Awarded 1st place in a seven-hour hackathon sprint.
Jadwalna AI
Active Prototype
Smart itinerary planning engine for Saudi Arabia with Expo 54 client, Fastify 5.2 constraint solver, Next.js 16 sharing, 1,000+ OSM Riyadh venues, and Saudi dialect NLP rules.
Uniapy
Active Build
Bilingual admissions and education consultant CRM built with Next.js 15.2, Prisma 6.5, Jose JWT RBAC, dynamic student profile extraction, and AR/EN RTL triage queues.
RoutineAI
Shipped PWA · Active
Student execution OS with deterministic scheduling, reminders, focus tools, alarms, and offline IndexedDB state. Passed 106/106 repository tests plus production build, lint, typecheck, and secret scan.
Additional public work: StudyRoot AI, Reliability Guard, Web Dev Skills, Lary OS, and MCOS. See the complete project directory →
Academic & competitive
Biohub Cell Tracking — Kaggle
Three-model 3D U-Net ensemble with test-time augmentation and graph repair; public score 0.917, rank #445 at the captured point.