Diffusion Models Machine Learning Expert

Responsibilities - Design, implement, and evaluate diffusion model architectures including DDPM, score-based, flow matching, and latent diffusion approaches - Develop and experiment with novel sampling strategies, noise schedules, and guidance techniques to improve generation quality and efficiency - Fine-tune and adapt pre-trained diffusion models for specific domains, modalities, and downstream tasks - Conduct rigorous benchmarking of diffusion models across perceptual quality, diversity, and controllability metrics - Document methodologies, experimental results, and technical approaches clearly and reproducibly

Required qualifications - Published researcher with at least one first-author publication in a peer-reviewed venue (e.g., NeurIPS, ICML, ICLR, CVPR, or equivalent) - Master's or PhD in Machine Learning, Computer Science, Statistics, or a related quantitative field - Deep, demonstrated expertise in diffusion models, score-based generative models, or flow-based approaches - Strong problem-solving skills and ability to work independently on open-ended research and engineering tasks

Preferred qualifications - Hands-on experience with leading diffusion model frameworks and codebases (e.g., Stable Diffusion, EDM, DiT, Consistency Models, or similar) - Familiarity with advanced conditioning and control mechanisms (e.g., ControlNet, classifier-free guidance, IP-Adapter, or similar) - Experience applying diffusion models beyond images — e.g., video, audio, 3D, or scientific data generation - Background in TA'ing or teaching generative modeling, deep learning, or computer vision courses

Why apply - Flexible Time Commitment – Work on your schedule while tackling meaningful research challenges - Startup Exposure – Work directly with an early-stage Y Combinator-backed company, gaining hands-on experience that sets you apart - Exceptional Pay – Project-based pay ranges from $150–$200/hour - Portfolio Building – Gain experience on frontier diffusion model research and applications - Professional Growth – Sharpen your skills on varied, challenging generative modeling tasks across modalities

Employment type: Contract Time commitment: 10 hours/week Location: Remote