Open to remote opportunitiesBASED IN PAKISTAN / WORKING EVERYWHERE

Hamza Asif / Full-stack engineer

Voice agents.Web products.Real-time 3D

ENGINEERING / INTERACTION / DELIVERY Move your cursor to explore

I build voice agents, web apps, and real-time 3D tools. Recent work includes streaming audio, video dubbing, and model conversion for Apple AR.

Explore the workGet in touch
Currently building voice and outreach agents at ZicsolDownload résumé

What the work changed

First audio 15s to 2s. English video dubbed in Urdu. GLB to USDZ ready for Apple AR.

See it in the work

Selected builds

Three builds.Three hard problems.

Voice latency, video dubbing, and a 3D model ready for Apple AR.

Selected work / 01

The work,
up close.

Voice agents, dubbing, AR conversion, and computer vision. What I built and what changed.

VOICE AI / FREELANCE01 / 05

SpeakUp

15s → 2s
View caseClose case
EXPLORE THE WORKFLOW
AFTER / 02

A single WebSocket stream carries both text and audio.

SpeakUp · freelance project2s to first audio chunk
VOICE AI / FREELANCE/01

A conversation. Without the wait.

SpeakUp — a mobile voice agent with a streaming pipeline rebuilt around a single WebSocket connection.

Problem
Text used SSE while audio used request/response. Receiving the first audio chunk took 15 seconds.
Approach
Replaced the split transport with one WebSocket stream for both text and audio, connecting the Flutter app to the Node.js backend.
Result
Time to the first received audio chunk fell from 15 seconds to 2 seconds.
  • Flutter
  • Node.js
  • WebSockets
SpeakUp on Google Play
LANGUAGE AI / HACKATHON02 / 05

Awaaz AI

English → Urdu
View caseClose case
WORKFLOW OVERVIEW
01English video
02Speech + translation
03Urdu dubbing
Uplift AI / LUMS hackathonEnglish → Urdu
LANGUAGE AI / HACKATHON/02

Awaaz AI

English-to-Urdu video dubbing, built for the Uplift AI / LUMS hackathon.

Problem
Make English video content accessible to Urdu-speaking audiences.
Approach
Built a seven-step dubbing pipeline using speech processing, translation, Urdu speech generation, and video assembly.
Result
An English-to-Urdu dubbing workflow integrating Uplift AI speech technology.
  • Whisper
  • Groq
  • Uplift Orator
  • Pyannote
  • Demucs / Modal
  • FFmpeg
3D / BLENSPARK03 / 05

Apple AR

GLB → USDZ
View caseClose case
WORKFLOW OVERVIEW
01GLB model
02Real-time conversion
03USDZ / Apple AR
BlenSpark · 3D & ARGLB → USDZ
3D / BLENSPARK/03

From a model to your space.

Real-time GLB-to-USDZ conversion for Apple AR, with AR video optimization.

Problem
Bring GLB models into Apple AR workflows that require USDZ.
Approach
Implemented real-time model conversion and optimized video for the AR experience.
Result
A conversion workflow connecting 3D assets to Apple AR.
  • GLB
  • USDZ
  • Apple AR
VOICE SYSTEMS / BLENSPARK04 / 05

Voice systems

~8s → <2s
View caseClose case
WORKFLOW OVERVIEW
01Pakistani telephony
02Python SIP integration
03Voice agent
BlenSpark · voice platform~8s → <2s
VOICE SYSTEMS / BLENSPARK/04

Voice AI, connected to real calls.

Voice agent engineering with a custom Python SIP integration for Pakistani telephony.

Problem
Slow voice responses and the need to connect AI conversations to local telephony.
Approach
Optimized the voice pipeline and built a custom Python SIP integration.
Result
Voice response latency reduced from approximately 8 seconds to under 2 seconds, with approximately 80% lower call costs.
  • Python
  • SIP
  • Voice AI
COMPUTER VISION / BLENSPARK05 / 05

WaveFront

Image → floor mask
View caseClose case
WORKFLOW OVERVIEW
01Room image
02Floor segmentation
03Floor region
BlenSpark · computer visionImage → floor mask
COMPUTER VISION / BLENSPARK/05

See a different floor.

Computer vision floor segmentation for room imagery.

Problem
Identify the floor region in a room image for a flooring visualization workflow.
Approach
Built a computer vision segmentation project to isolate the floor region.
Result
A floor segmentation workflow for visualizing changes in a room.
  • Python
  • Computer Vision
ALSO IN THE TOOLBOX

CRM systems. 3D configurators. Next.js websites.

Try the 3D configurator

About / 02

Hi, I'm Hamza.
I build across layers.

~2.5 YEARS

Across full-stack development
and applied AI engineering.

I've worked on the call, the server behind it, and the interface on the other end.

I'm based in Pakistan and currently build voice and outreach agents at Zicsol.

At BlenSpark, I moved from intern to full-stack developer and worked on voice AI, computer vision, 3D, and web apps. I completed a BS in Artificial Intelligence at UMT in July 2026.

I'm available for remote roles, freelance work, and open-source collaboration.

See my GitHub

Experience / 03

Where I've
worked.

Download résumé ↓
Aug 2026 — PresentCURRENT

AI Automation Engineer

Zicsol

Building voice and outreach agents.

Sep 2024 — Jul 2026

Intern → Full-Stack Developer

BlenSpark

Worked on voice AI, Python SIP integration, floor segmentation, 3D and AR workflows, and full-stack products.

Completed Jul 2026

BS Artificial Intelligence

University of Management and Technology

Technologies I use

Technology stack

Discover my work

Front-End

06 tools
  • [React]
  • [Next.js]
  • [TypeScript]
  • [Tailwind CSS]
  • [GSAP]
  • [Three.js / R3F]

Back-End

04 tools
  • [Python]
  • [Django / DRF]
  • [FastAPI]
  • [Node.js / Express]

Contact / 04

Have a project?Let's talk.

I'm open to remote engineering roles and freelance projects involving voice AI, web apps, or 3D.

LinkedIn GitHub

Start a conversation.

Tell me about your team, the problem you're solving, or a product you want to bring to life.

Connect on LinkedIn