Technical Co-Founder (Equity Based) — Video AI / Computer Vision

We are looking for a co-founder (equity-based) to join our early-stage tech startup in the video domain. This is a chance to help shape the future of intelligent video creation and editing from the ground up.

About us: We are a 100% bootstrapped startup, currently building our MVP in stealth mode, with a planned release in 2026. This is the perfect time to join at the ground level and have a true impact on both technology and company direction.

Beyond the technical expertise, we are seeking a partner who is:

• A strong communicator and collaborative team player.
• Experienced in startups, ideally with a proven track record as a co-founder or early-stage contributor.
• Able to commit at least 1/3 of their time to building the company.
• Passionate about pushing boundaries in video, AI, and computer graphics.
• (Bonus) Background in computer graphics research.

If you’re driven, resourceful, and excited by the challenge of building breakthrough technology with real product impact — we want to talk.

Key Responsibilities

• Video Understanding Pipeline: Design, train, and deploy advanced deep learning models for video analysis:
• Object detection, tracking, recognition
• Semantic & instance segmentation
• Action & event recognition
• Camera motion analysis (shake, dolly, zoom)
• Scene boundary detection, saliency detection, content classification
• Aesthetic feature analysis (composition, lighting, color palettes)
• Generative Models Research: Innovate with GANs, Diffusion Models, and VAEs to create novel effects, transitions, and style transfers tailored to video content.
• R&D and Prototyping: Stay at the cutting edge of computer vision and machine learning research. Rapidly prototype, test, and validate new approaches.

Required Qualifications

• M.S. or Ph.D. in Computer Science, Electrical Engineering, or a related field with a focus on Machine Learning or Computer Vision.
• 3+ years of hands-on experience building and deploying CV/ML models in a production environment.
• Strong theoretical and practical understanding of deep learning architectures (e.g., CNNs, RNNs, LSTMs, Transformers) for video and image analysis.
• Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.
• Proven experience in classic and modern computer vision techniques for tasks like feature extraction, optical flow, and 3D reconstruction.
• Excellent problem-solving skills and the ability to translate a high-level vision into a concrete technical roadmap.
• Strong communication skills and a collaborative mindset.

Preferred Qualifications

• Audio signal processing (beat detection, speech-to-text, mood analysis).
• Familiarity with 3D graphics, rendering pipelines, camera tracking.
• Experience with generative models for video/image synthesis.
• Published research, open-source projects, or portfolio in the field.
• Personal interest in filmmaking, VFX, or motion graphics.