Computer Vision Engineer
Location: New York, NY (On-site)
Industry: Artificial Intelligence | Generative Media | Computer Vision
Job Type: Full-Time
Compensation: Competitive Base + Founding-Level Equity
A cutting-edge AI research startup is assembling a pioneering founding team to build a generative video system with world-class fidelity and creativity. Backed by top-tier investors and led by seasoned deep learning experts, this stealth-mode lab is developing a new paradigm for creative automation—blending computer vision with generative modeling to reshape how media is produced.
This is a rare chance to help define a category-defining product at the intersection of AI, film, and design. You’ll contribute as a builder, inventor, and collaborator, with direct influence over systems that generate production-ready, coherent video outputs at scale. The ideal candidate brings deep expertise in computer vision and generative modeling, paired with a builder’s mindset and a passion for quality.
Key Responsibilities
- Build generative vision systems that produce multi-minute, temporally coherent video sequences free from flickering, warping, or visual artifacts.
- Translate creative controls (relighting, retiming, camera movement, typography) into structured model inputs for real-time rendering pipelines.
- Architect self-repair loops that detect and correct generative flaws prior to delivery.
- Coordinate multi-shot generative workflows, ensuring visual consistency, continuity, and reusable assets across scenes.
- Scale inference pipelines using model distillation, quantization, multi-GPU orchestration, and progressive rendering strategies.
- Collaborate closely with artists and product stakeholders to align on editorial intent, quality benchmarks, and creative direction.
- Design evaluation frameworks that reflect studio-level quality expectations and iterate toward perfection.
Qualifications
- Advanced knowledge of computer vision and generative models (images and video).
- Experience architecting, training, and scaling video generation systems.
- Demonstrated success building production-grade generative video pipelines.
- Broad understanding of research literature across CVPR, ICCV, ECCV; SIGGRAPH publications are a strong signal.
- Deep familiarity with temporal consistency, model controllability, and multimodal generation.
- Strong hands-on coding ability in PyTorch or JAX.
- Ability to collaborate with cross-functional teams in fast-paced, high-ownership environments.
Strong Plus
- Experience building real-time inference pipelines with progressive render and sub-second latency.
- Background in generative 3D (NeRFs, 3D Gaussian Splatting) or multimodal intelligence.
- Interest in creative AI and computational aesthetics.
Ideal Candidate Profile
- Thinks like a founder, builds like an engineer, and iterates like a scientist.
- Views creative AI as a transformational technology, not just an optimization problem.
- Thrives in a zero-to-one environment with high ambiguity and high standards.
- Ready to relocate to NYC and commit long-term to a moonshot vision.
Why Join?
- Founding-level equity and ownership over a category-defining product.
- Collaborate with elite researchers and artists to define the future of generative media.
- Shape a new creative medium powered by AI, from the ground up.
- Work on ambitious, deeply technical problems with real-world creative impact.
- Access to meaningful GPU resources and compute scale.
About Blue Signal:
Blue Signal is an award-winning, executive search firm specializing in various specialties. Our recruiters have a proven track record of placing top-tier talent across industry verticals, with deep expertise in numerous professional services. Learn more at bit.ly/46Gs4yS
