Back to selected work

2023 - Present

Automated podcast clip generation

Co-founder / AI Developer, Mecene.ai

Built an AI system that transforms long podcast videos into social-ready one-minute clips without manual editing.

Private product
PythonPyTorchOpenCVWhisperDockerRunpod

Fine-tuned ChatGPT and Gemini on a YouTube-derived dataset to improve clip selection.

Implemented speaker detection and auto-framing to keep the active speaker centered on screen.

Deployed a decentralized GPU-backed pipeline on Runpod to split processing into reliable stages.

Context

At Mecene.ai, the goal was to turn long-form podcast episodes into short clips that were actually worth publishing. The hard part was not only cutting video. It was choosing segments with enough value, detecting who was speaking, and producing something that felt edited instead of obviously automated.

What I built

I worked on the end-to-end system that takes a podcast video and turns it into multiple short clips.

Why it was interesting

This project sits at the intersection of product and research. A technically correct output was not enough. The clips had to feel engaging, correctly framed, and useful for distribution on social platforms.

That meant balancing model quality, infrastructure cost, and product speed at the same time.

Technical focus

Engineering decisions

One of the main design decisions was to treat the system as a pipeline instead of one monolithic job. That made it easier to isolate GPU-heavy work, improve reliability, and evolve individual stages without rebuilding the whole flow.

The other important constraint was quality. A clip that was technically valid but boring or badly framed was still a failure, so model behavior and presentation quality had to be optimized together.

Reach out

Want more detail than I can share publicly?

I can walk through the architecture, tradeoffs, and implementation details for private work in a conversation.