Yirmeyahu Mwangelwa

AI Engineer

I build and deploy production AI systems—voice synthesis, video generation, content pipelines, and serverless GPU infrastructure. I run Zambian Tech, LLC, where I've shipped everything from fine-tuned TTS models to end-to-end content automation platforms. 4+ years of professional software engineering experience.

See my work Contact

What I build

capabilities

Voice & Audio

Fine-tuned TTS, voice cloning, CPU and GPU inference.

Video & Media

Text-to-video, image-to-video, rendering pipelines.

Content & NLP

Automated publishing, translation at scale, LLM pipelines.

Featured projects

view all →

AssetFlow

Flagship AI production platform

End-to-end platform orchestrating content pipelines from creation through narration, rendering, and delivery. Built across three major versions.

Python Django PostgreSQL AWS Celery

Production · 3 major versions

F5-TTS Voice Cloning

Custom voice synthesis on serverless GPU

Fine-tuned the F5-TTS model on custom voice recordings. Deployed on serverless GPU with custom Docker container and CUDA 12.1.

PyTorch F5-TTS CUDA Docker RunPod

Production · RunPod

AI Video Generation

5B-parameter diffusion model

Built and deployed the Wan2.2-TI2V-5B diffusion model on serverless GPU for text-to-video and image-to-video generation at 720p.

Wan2.2 Diffusion Models Docker RunPod

Built · Previously on RunPod

Want to work together?

I'm open to AI engineering roles, consulting, and interesting collaborations.

Get in touch