Overview
Crisalix is the world’s leading technology company in 3D imaging and aesthetic simulation, leveraging AI, computer vision and augmented reality to create accurate 3D reconstructions of the human body and lifelike procedural simulations.
About the Role
We are seeking a Mid‑Level Computer Vision & 3D Deep Learning Engineer to develop and deploy models that understand and reconstruct the visual world. You will contribute to production‑grade pipelines that transform multi‑view 2D images into high‑quality 3D reconstructions using statistical shape models, implicit neural representations, and texture synthesis.
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, evaluating 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 (e.g., TorchScript/JIT, Triton Inference Server).
Required Qualifications
* 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 and learning‑rate scheduling.
* Strong Python skills; proficiency with PyTorch (primary) or TensorFlow.
* Comfortable reading and implementing methods from academic papers.
* Fluent or proficient in English (Spanish is a plus).
Preferred Qualifications
* Experience with 3D vision techniques (e.g., NeRFs, differentiable rendering, SLAM).
* Understanding of implicit surface representations: signed distance functions, occupancy networks, NeRF/neural radiance fields.
* Familiarity with classical 3D fitting approaches such as statistical shape models, ICP, mesh deformation.
* Knowledge of differentiable rendering concepts: ray marching, sphere tracing, volume rendering.
* Experience with libraries such as Open3D, PyTorch3D, or OpenCV.
* Experience with experiment‑tracking tools (MLflow, Weights & Biases) and reproducible training pipelines.
* Experience deploying models to production environments with Docker for reproducibility and scalability.
* Understanding of GPU optimization and performance tuning.
* Background in geometry, linear algebra, or graphics.
Benefits and Compensation
* Competitive salary and benefits package.
* Structured onboarding, mentoring, performance reviews, and training plans.
* Flexible hybrid model: 2–3 days per week in our Barcelona office, remote work otherwise.
* Opportunities for professional growth within an international environment and a collaborative culture.
EEO Statement
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.
#J-18808-Ljbffr