Machine Learning Engineer with 5+ years of experience designing and training deep generative models, with a Master’s degree in Image Processing and Computer Vision. Proven track record building end-to-end ML pipelines across research and cross-functional industry projects in Germany and internationally.
Core expertise in generative modeling (GANs, diffusion models, VAEs), sequence learning, and computer vision, applied to domains including human motion, 3D data, and multimodal systems. Experienced collaborating with engineers, domain experts, and academic partners to take models from prototype to deployable output.
Published researcher (CVMP 2024 Runner-Up Best Paper) with a bias toward practical impact: clean, reusable model architectures, rigorous evaluation, and cross-domain transferability.
Skills
ML & AI
PyTorch | Deep Learning | Generative Models (GANs, VAEs, Diffusion Models, Normalizing Flows) | Transformers | LLMs | Computer Vision
3D & Motion
3D Data Processing | Motion Capture Analysis | SMPL/Body Models | Pose Estimation | Avatar Animation
Engineering
Python (8+ years) | C++ | NumPy | OpenCV | Git | TensorBoard | Inference Pipeline Optimization
Experience
Fraunhofer HHI, Germany. Research Associate (January 2021 – December 2025)
Developed and trained deep generative models (GANs, diffusion, transformers) for human motion synthesis and avatar animation, contributing to 4 EU-funded projects (LUMINOUS, SPIRIT, MoDL, INVICTUS) spanning AI, XR, and interactive media.
- Developed a modular motion tokenizer achieving 43.6% improvement in hand reconstruction and 42.1% in lower-body accuracy (MPVPE) over baseline; adopted as the backbone for a subsequent gesture synthesis system and ongoing integration into a project pipeline.
- Built and benchmarked a GAN-based motion synthesis model trained on performance capture data, improving motion diversity by 7.3% and training coverage (motion fidelity) from 88-98% to 99-100% compared to baseline, with improved motion controllability and physical realism.
- Mentored a Master’s student on transformer-based co-speech gesture synthesis, delivering a working system on the motion tokenizer.
- Produced technical documentation, progress reports, and milestone deliverables for EU project partners and non-technical stakeholders.
- Presented technical results to 15+ academic and industry partners across AI, XR, and simulation domains; represented the group at Web3d, CVMP, and EuroXR.
- Co-authored a peer-reviewed paper awarded a Runner-Up Best Paper at CVMP 2024.
Vicomtech, Spain. Computer Vision Intern & Master’s Thesis (February 2020 – June 2020)
Built a real-time generative system for live artistic performance, integrating pose estimation, GAN-visual synthesis, and audio feature extraction into a unified interactive pipeline.
- Trained StyleGAN on custom datasets to produce domain-specific visual styles for live output; optimized inference pipeline to sustain 15-30 FPS under real-time performance constraints.
- Integrated multi-person pose estimation and audio feature extraction as multimodal conditioning inputs for dynamic latent space manipulation.
- Delivered a fully functional prototype to a cultural venue partner, demonstrated live for potential deployment in a public installation.
Université de Bordeaux, France. Student Researcher (January 2019 – December 2019)
Conducted research on the challenges of object detection in immersive image formats, focusing on the effects of spherical and equirectangular projections on model performance. Analyzed how geometric distortions introduced by panoramic projections impact detection accuracy and spatial consistency, and methods to mitigate them. Reviewed state-of-the-art deep learning methods for object detection (e.g., YOLO, Faster R-CNN) and evaluated their applicability to 360° image data.
VASS LATAM (Client: AXA), Colombia. Consultant – Software Developer (October 2017 – August 2018)
Developed core software components for AXA within a highly regulated enterprise environment, following strict documentation, versioning, and quality assurance protocols. Contributed to system integration workflows using Microsoft BizTalk Server and supported backend development tasks within the .NET ecosystem. Collaborated with a consulting team to deliver client-facing solutions aligned with AXA’s internal software standards.
Pontificia Universidad Javeriana, Colombia. Student Researcher (January 2016 – July 2016)
Conducted research on image quality assessment methods for fused infrared and visible spectrum imagery. Investigated natural scene statistics in multi-spectral image data and developed models that better approximate human perceptual quality. Work involved statistical feature extraction, perceptual modeling, and benchmarking against existing image fusion evaluation techniques.
Achievements:
- Developed two image quality evaluation models that outperformed existing metrics in correlation with human subjective ratings, achieving improvements of +0.14 absolute (~25% relative) and +0.16 absolute (~20% relative) when compared to the best performing baselines.
- Presented research at ICASSP 2017 and published findings in IEEE Transactions on Image Processing (TIP).
- Demonstrated the application of perceptual modeling to multi-spectral image fusion in a cross-modal context.
Continental Automotive GmbH, Germany. R&D Intern (April 2015 – July 2015)
Built reporting tooling for electronic control units (ECUs) test analysis using C# and .NET, generating Excel-based statistical summaries to support automotive testing workflows.
Academic Training
- Université de Bordeaux, Universidad Autónoma de Madrid, Pázmany Péter Katolikus Egyetem - MSc Image Processing and Computer Vision (2018 - 2020): Fully funded Erasmus+ student.
- Pontificia Universidad Javeriana de Cali - BSc in Electronics Engineering (2010-2017): Honor distinction for Thesis Natural Scene Statistics of Long Wave Infrared and Visible Images, Merit awards.
- Karslruhe Institute of Technology (2015): Exchange semester, DAAD scholarship.
Languages
| Language | Level | Certificate |
|---|---|---|
| Spanish | Native | |
| English | C1 | IELTS - 7.5 |
| German | B2 | TestDaF |
| French | A2 |
Programming Languages
| Language | |
|---|---|
| Python | 8+ years |
| Matlab | 6+ years |
| C++ | 3+ years |
| C | 2+ years |
| C# | 1+ years |
Awards & Recognition
- Runner-Up Best Paper Award, CVMP 2024. Recognized for innovation in generative motion synthesis.
- Erasmus+ Joint Master’s Degree Scholarship, 2018-2020. Competitive full scholarship for international MSc program across three European universities.
- DAAD Young Engineers Scholarship, 2014-2015. Full sponsorship for academic at KIT, Germany.
- Top Graduating Student in Electrical and Electronics Engineering, 2017, Pontificia Universidad Javeriana.
- Undergraduate Thesis Honor Distinction, 2016. Outstanding research recognition; led to publication in IEEE Transactions on Image Processing and presentation at ICASSP 2017.
- ICASSP 2017 Travel Grant and Conference Presentation, New Orleans, USA. Presented thesis research at IEEE flagship signal processing conference.