? Looking for a Technical Co-Founder — AI/ML | Video Generation | Generative AI
OUR main goal is to reduce the latency and generate frame images in miliseconds
I’m currently exploring an early-stage startup idea in AI-generated video / Video Foundation Models , and I’m looking for a technical co-founder who is deeply interested in the underlying ML research and wants to build something from the ground up.
This is currently at the ideation + research stage . The goal is to explore whether we can build a differentiated low latency video-generation technology rather than simply wrapping existing APIs.
? Who I'm looking for
Someone with strong foundations in:
- Deep Learning
- Mathematics for ML
- Transformers & Attention
- Generative AI
- Diffusion Models / Flow Matching
- Computer Vision
You should understand what is happening inside the model , not just know how to call an API.
For example, you should be comfortable discussing:
→ Self-attention and why it works
→ Transformer architecture and positional/temporal representations
→ Diffusion and flow-matching mathematics
→ Vision Transformers / DiT
→ Spatial + temporal modeling
→ Video latent representations
→ Temporal consistency
→ Training and inference bottlenecks
→ GPU optimization and distributed training
? What we would explore The initial focus would be research and experimentation around:
Image → Video
Video → Video
Real-time / low-latency video generation The exact product direction is still being validated, so I’m looking for someone who enjoys research, experimentation and building from first principles .
? What I’m looking for in a co-founder
More important than degrees or titles:
Curiosity + strong mathematical understanding + ability to implement research papers + willingness to experiment.
You don't necessarily need a PhD. If you've independently studied and implemented up-to-date generative models and can explain the mathematics behind them, I'd love to talk.
? Stage
Idea / Research / Validation
This is an opportunity to join extremely early and have significant ownership over the technology, research direction and eventual product .
If you're interested in building video-generation models from the ground up , DM me with:
1. Your background
2. ML/DL projects you've built
3. Papers/models you've implemented(if any)
4. GitHub / portfolio (if available)
I'm especially interested in connecting with people who are genuinely excited about Generative AI + Computer Vision + Research .