Nothing Ear: rush hour, on mute
A call with Maa on a packed Mumbai local, two loud strangers, and one tap that brings her voice back. Hinglish.
Open to GenAI roles in Delhi NCR or remote

I build AI that films ads. As a core engineer of an AI Creative Studio for brands and agencies, I turn one product photo into a 15-second video ad in about 5 to 10 minutes, for about $2. Every video on this page is AI-made: nothing was filmed.
Watch the 90-second filmHow I build AI ads + 4 disasters I fixedA call with Maa on a packed Mumbai local, two loud strangers, and one tap that brings her voice back. Hinglish.
A Manhattan jackhammer at 6 am, a tap on the stem, and the run turns into a rock track. 12 s.
2 AM in a Mumbai PG, a flatmate finds a dhol, and one earbud ends the night's noise. UGC, 16 s.
A US dorm roommate who never sleeps, and a mini-fridge stacked with cold brew that explains it. 30 s.
In Seoul, Umma bins twelve skincare bottles, then steals the one serum her daughter kept. 30 s.
Her office, one locked look across three clips, captions with the key words in lime, and an end card.
A storyboard shot list played out on a market street, a café table and a shop counter.
A natural speaking pace and one gesture per line, landing on its word, across five clips.
A brand used to pay an influencer about $120 to $300 and wait days for one video ad. The Creative Studio makes it in minutes for about $2: roughly 98% less per ad.
A product photo, a brand kit or a winning ad.
Gemini Flash reads the reference: 77 s down to 16 s.
LLM writers draft three scripts in five beats.
Video models film each clip, with a provider fallback.
Word checks, drifted clips filmed again, captions on.
A 15-second ad, ready to run, for about $2.
A product photo or a reference ad goes in. I rebuilt the reference read on Gemini Flash: 77 s down to 16 s.

From the hook to the call to action, on OpenAI with Gemini as the backup, in English or Hinglish.

Seedance on BytePlus Ark first with KIE as the fallback, Veo and Gemini Omni for Hinglish. The product stays the one in the photo.

51 caption styles, a word-accuracy check and drifted clips filmed again, so the ad arrives ready to run.

D2C brands and agencies paid influencers for every video, waited days, and could not test enough hooks.
The video engine end to end, from the first port to production and a V2 canvas, built with the BytePlus and Google Gemini teams.
Demoed to 12+ agencies and D2C brands across India, the US and Canada, at about $2 an ad.
POV: your flatmate found a dhol at 2 AM.
Exams tomorrow. Zero sleep tonight.
One tap. The room goes quiet.
Seedance · Ark
Seedance · Ark
KIE fallbackOne of 51 styles, ranked for this video, kept clear of faces.
Forward-deployed · incident log
Your product and words inside the reference ad's own timing. Reading the reference fell from 77 s to 16 s.
Up to 5 new LLM-written hooks per ad, gated at 75% word accuracy and stitched so no frame repeats.


Hook 1 of 5
Ranked per video and kept off faces; a caption error falls back and the ad still ships.
When our video provider stopped serving videos, I called the BytePlus team that night and moved the pipeline to Seedance on Ark.
Nano Banana, GPT Image, Seedream, Qwen, Grok and FLUX, matched to each creative by ratio, resolution and cost.

Generative AI and LLMs
Video and image generation
Engineering