Mid-Level Computer Vision & 3D Deep Learning Engineer
14 hours ago
Madrid
Crisalix – Redefining Aesthetic Visualization Crisalix is the world’s leading technology company in 3D imaging and aesthetic simulation. Leveraging the latest advancements in Artificial Intelligence , Computer Vision and Augmented Reality , our proprietary technology enables the creation of highly accurate 3D reconstructions of the human body and lifelike simulations of aesthetic procedures. With a global presence across five continents , Crisalix empowers some of the world’s most recognized plastic surgeons and clinics to enhance patient trust, visualize treatment outcomes, and deliver exceptional results. Our solutions are designed not only to elevate the patient experience , but also to drive tangible business growth for clinics—helping them stand out in an increasingly competitive market, expand their offerings, and increase revenues. As we continue to grow worldwide, we are committed to setting new standards in innovation and customer success . We seek to inspire through excellence—focusing on measurable outcomes, strong data analytics, and operational precision to ensure Crisalix remains a transformative force in the aesthetic industry. Crisalix Challenge Crisalix business is growing after our history of more than 15 years, and we have new products that require the best talent in our team. Are you ready for the challenge? Then this might be your opportunity! We are looking for a successful Mid-Level Computer Vision & 3D Deep Learning Engineer to join our fantastic team. At Crisalix, we empower our product teams to solve hard problems – customer problems and business problems – in ways that our customers love, yet work for our business. Our product teams are cross-functional and durable, generally composed of a product manager, a product designer, and several engineers. The team We are a market leading multinational company focused on innovation and developing state-of-the-art 3D to bring aesthetic consultations to the next level. That's why we are looking for you! We are looking for specialists who want to be part of this challenging adventure. About the Role We are looking for a Computer Vision Engineer with a solid background in deep learning and 3D data processing to join our team. You will work on developing and deploying models that understand and reconstruct the visual world, contributing to production-grade pipelines that take multi-view 2D images and produce high-quality 3D reconstructions (from statistical shape models to implicit neural representations and texture synthesis). at the intersection of classical 3D geometry and modern neural approaches. This role is ideal for someone with 2–3 years of hands-on experience who enjoys bridging research and production, and is comfortable designing and training pipelines, evaluating reconstruction quality, and integrating your work into a complex multi-stage system. Responsibilities Research, prototype, and integrate new deep learning algorithms from recent literature (NeurIPS, CVPR, ICCV, ECCV) to improve 3D reconstruction quality. Develop and maintain deep learning components for multi-view reconstruction, landmark detection, segmentation, inpainting, and view-consistent shape fitting. Implement and tune custom training pipelines and loss functions, and evaluate their impact on mesh and texture quality. Design and run quantitative evaluation experiments using metrics such as reprojection error, surface-to-surface distance, and perceptual quality scores Export and deploy trained models for inference (TorchScript/JIT, Triton Inference Server,..) The skill set 2–3 years of hands-on experience in computer vision and deep learning research or applied engineering Solid understanding of camera models, projective geometry, and multi-view geometry (epipolar geometry, camera calibration, reprojection) Experience training and debugging neural networks end-to-end, including custom loss functions, learning rate scheduling, and training stability Comfortable reading and implementing methods from academic papers Strong Python skills; proficiency with PyTorch (primary) and/or TensorFlow Comfortable working in a research codebase with complex multi-stage pipelines Fluent or proficient in English (Spanish is a plus). We would also value highly positively Experience with 3D vision techniques (e.g. NeRFs, differentiable rendering, SLAM). Understanding of implicit surface representations: Signed Distance Functions (SDFs), occupancy networks, NeRF/neural radiance fields Familiarity with classical 3D fitting approaches: statistical shape models (PCA-based), iterative closest point (ICP), mesh deformation Knowledge of differentiable rendering concepts: ray marching, sphere tracing, volume rendering Familiarity with libraries such as Open3D, PyTorch3D, or OpenCV. Experience with experiment tracking tools (MLflow, W&B) and reproducible training pipelines Experience deploying models to production environments, using Docker to ensure reproducibility and scalability. Understanding of GPU optimization and performance tuning. Background in geometry, linear algebra, or graphics. What we offer A technically deep role at the frontier of 3D AI — far from a standard MLOps or fine-tuning position. You’ll be part of a team that reads papers, runs ablations, and turns research into real-world production systems. At Crisalix, we actively support your professional growth within an international environment, working alongside a strong team and leveraging state-of-the-art technology. You’ll have the freedom to explore new ideas, propose architectural changes, and continuously push the boundaries of innovation. We offer a competitive salary and benefits package, along with structured onboarding, mentoring, performance reviews, and training plans to help you advance your career. We also believe work should be enjoyable: from team events to a collaborative culture, we make sure there’s room for fun. In terms of work-life balance, we offer a flexible hybrid model: spend 2–3 days per week in our Barcelona office and work remotely the rest of the time, giving you the best of both worlds while maintaining a healthy balance. About Crisalix Crisalix is the world's leading tech company in the field of 3D aesthetic simulation. Its unique technology is based on the most recent advances in Artificial Intelligence, Computer Vision and Augmented Reality and it permits the creation of highly accurate 3D reconstructions of human bodies and the simulation of aesthetic procedures on top. Its disruptive technology caters to some of the world's most recognized plastic surgeons and clinics across 5 continents. Do you want to know more about us? Please look at our website: And please see our videos: is an open secret we are the first company to: Release an app integrating the Structure 3D Sensor in the medical field: Launch a 4D/VR app in the plastic surgery field: Apply Augmented Reality technology to the plastic surgery sector: We would love to get to know you! If you would like to know us too, please apply in English or send an email to Is this role not an exact fit? Sign up to keep in touch and we’ll let you know when we have new positions on our team. Crisalix is committed to equality of opportunity for all staff, and applications from all suitably qualified individuals are encouraged, regardless of age, disability, sex, gender reassignment, sexual orientation, pregnancy and maternity, race, religion or belief and marriage and civil partnerships.