I am an AI/ML engineer and technical founder focused on building production-grade Gen AI systems and automation. Over the past 2+ years, I have designed RAG pipelines, LLm orchestration, and AI voice automation in SaaS products. I thrive on turning research into reliable software and delivering end-to-end products for real-world use. I code in Python, TypeScript, OpenAI API, FastAPI, and Next.js; I deploy on Vercel and Railway. I enjoy solving complex problems, building scalable architectures, and creating measurable impact for SMBs and teams through practical AI solutions.…

Habib

I am an AI/ML engineer and technical founder focused on building production-grade Gen AI systems and automation. Over the past 2+ years, I have designed RAG pipelines, LLm orchestration, and AI voice automation in SaaS products. I thrive on turning research into reliable software and delivering end-to-end products for real-world use. I code in Python, TypeScript, OpenAI API, FastAPI, and Next.js; I deploy on Vercel and Railway. I enjoy solving complex problems, building scalable architectures, and creating measurable impact for SMBs and teams through practical AI solutions.…

Available to hire

I am an AI/ML engineer and technical founder focused on building production-grade Gen AI systems and automation. Over the past 2+ years, I have designed RAG pipelines, LLm orchestration, and AI voice automation in SaaS products. I thrive on turning research into reliable software and delivering end-to-end products for real-world use.

I code in Python, TypeScript, OpenAI API, FastAPI, and Next.js; I deploy on Vercel and Railway. I enjoy solving complex problems, building scalable architectures, and creating measurable impact for SMBs and teams through practical AI solutions.

See more

Language

English
Fluent

Work Experience

AI Engineer (Freelance) at Pashtun Intelligence
January 1, 2025 - Present
Developed an AI research dashboard with GPT-4 orchestration: path-to-brief generation, YouTube ingestion, and script generation on Next.js 14 + Supabase; reduced research-brief generation time from hours to minutes and implemented usage logging for governance.
AI Engineer & Founder at Calls Catch
January 1, 2024 - Present
Built a multi-tenant SaaS on Next.js and FastAPI with Stripe; automated AI-driven client acquisition, including multi-bank PDF/OCR to GPT-4 outputs; reduced forensic review time from weeks to minutes with court-ready structured reports; designed systematic prompt engineering (v2.1) aligned to ACFE/AICPA standards and JSON-mode structured outputs; implemented a Google Sheets CRM with TEST_MODE and AU compliance; deployed on Vercel and Railway with JWT authentication and audit logging; migrated from a Streamlit prototype to production, delivering end-to-end product from calls-to-catch to invoicing.

Education

bachelor information technology at king's own institute
September 30, 2023 - November 30, 2026
Bachelor of Information Technology at King's Own Institute
January 1, 2023 - January 1, 2026

Qualifications

Search Engine Optimization — Digiskills.pk
January 1, 2022 - June 6, 2026

Industry Experience

Software & Internet, Professional Services, Other
    AI Voice Ordering Platform for Independent Restaurants

    Built a full-stack AI phone ordering platform from scratch for
    independent restaurants in Australia. When a customer calls the
    restaurant’s number, an AI assistant named Maya answers, takes
    the food order conversationally, and sends it live to a kitchen
    tablet dashboard — no staff needed to answer the phone.

    What the system does:

    • AI agent handles the full order conversation — menu,
      modifiers, customer name, pickup time, order confirmation
    • Orders appear in real time on a kitchen tablet (kanban board:
      New → In Kitchen → Ready for Pickup)
    • Complex calls transfer live to the owner’s mobile via Twilio
    • One AI agent serves unlimited restaurants dynamically — the
      correct menu and config loads per call based on which number
      was dialled
    • Restaurant owners manage hours, menu, and settings via a
      web dashboard

    Technical highlights:

    • Pre-warm cache loads menu data during the ring — eliminating
      startup silence before the agent speaks
    • Server-side variable resolution for Retell AI’s tool calling
      (platform limitation workaround)
    • Timezone-aware trading hours engine with special day overrides
    • Supabase Realtime subscriptions with polling fallback for
      the kitchen tablet
    • Role-based auth — admin and kitchen staff roles with
      separate access levels

    Stack: Retell AI · GPT-4.1-mini · Twilio · Node.js · Express ·
    TypeScript · Supabase · PostgreSQL · Next.js 14 · Tailwind CSS ·
    Railway · Vercel