RepeatMD is looking to build the next generation of AI-powered facial analysis and rejuvenation previews in the health and beauty space to allow users to see potential results of aesthetic and wellness treatments before visiting a clinic.
Requirements
- Strong track record with segmentation, detection, and diffusion-based generative models (SDXL, Stable Diffusion, etc.)
- Deep expertise in optimizing ML for scalability and efficiency (quantization, pruning, distillation)
- Strong engineering background: Python, PyTorch/TensorFlow, clean production code
- Hands-on experience deploying ML at scale in AWS/GCP/Azure
- Proven ability to balance speed, accuracy, and cost in real-world deployments
- Comfort reading and integrating with a .NET and React stack via clean service contracts.
- Experience with edge/low-compute deployment
Responsibilities
- Design and optimize computer vision models that transform real patient images into realistic, medically accurate “after” results.
- Evaluate and benchmark state-of-the-art models (segmentation, detection, SDXL/diffusion, LLM-based classifiers)
- Develop generative models for before/after treatment previews, ensuring realism, inclusivity, and clinical credibility
- Design inference pipelines optimized for low latency and high throughput
- Use model compression, quantization, and distillation to reduce compute costs while maintaining accuracy
- Leverage AWS (Lambda, Step Functions, SageMaker, GPU pipelines) or equivalent to build cloud-scale systems
- Build quality-control systems (blur detection, orientation/rotation correction, lighting checks)
Other
- Master's/PhD in Computer Science, Machine Learning, or equivalent practical experience
- 5+ years of experience in applied ML, with a focus on computer vision and generative models
- Experience in healthtech, medtech, or regulated AI environments
- Knowledge of bias mitigation and fairness techniques in ML
- Contributions to open-source or research publications in computer vision/generative AI
