Curriculum Vitae

Deep learning engineer for autonomous driving perception systems, focusing on multi-sensor fusion, foundation model optimization, and hybrid approaches combining classical computer vision with modern deep learning techniques. Develop and optimize production-scale 360° ground truth system processing high-volume sensor data from test vehicle fleets to evaluate and train autonomous driving products.

• Transformed early-stage system to production deployment, achieving significant accuracy improvements and performance gains through systematic optimization across classical and deep learning pipeline modules
• Provide technical guidance for team of engineers on architecture decisions, model selection, and deployment strategies
• Evaluate and integrate state-of-the-art foundation models with focus on memory optimization, inference speed, and production requirements
• Research and prototype novel approaches for enhancing ground truth system performance, adding new capabilities that enable new products and support additional stakeholders
• Contribute technical expertise across object detection, sensor fusion, and scene understanding projects beyond core ground truth development

Certified BEO Expert (Bosch Expert Organization) through peer nomination — a highly selective distinction awarded to engineers with recognized deep expertise. Provide cross-divisional consulting on advanced AI topics including foundation model optimization, multi-modal architectures, generative models, computer vision, and deep learning techniques for perception systems.

Led technical development of automotive radar electronics deployed globally across multiple platform generations. Managed international teams of 6-18 engineers coordinating design, validation, and integration workstreams. Served as primary technical interface with customers and suppliers.

Architected electronic modules including microcontrollers, MMIC radar ASICs, System ASICs, and radar SoCs with responsibility for hardware architecture, PCB design and layout, safety, thermal design, EMC compliance, and reliability.

Designed, validated, and tested electronic modules for automotive radar sensors deployed globally. Collaborated with customers and suppliers to develop solutions balancing cost, safety, reliability, and manufacturability for high-volume production.

Led cross-functional EMC compliance taskforce (10-15 members, 6 months) during pre-release validation crisis. Coordinated technical investigation across hardware, software, and integration teams, implemented corrective design changes, and secured regulatory compliance. Crisis management and technical leadership led to promotion to Technical Project Lead in 2019.

Lead Spain's first IEEE-HKN chapter through 3-year presidential cycle (President-Elect 2023, President 2024, Past President/Consultant 2025). Grew membership from 90 to 110+ members. Chapter earned 3 Key Chapter awards and 1 Outstanding Chapter distinction among 260 global IEEE-HKN chapters.

Launched strategic initiatives: established GitHub organization and YouTube channel for knowledge sharing, organized inaugural HKN-Talks series featuring expert presentations from academia and industry. All leadership activities conducted in Spanish.

Roles: Corresponding Secretary (2022), President-Elect/President/Past President (2023-present).

Research collaboration on Free Viewpoint Video (FVV) Live system for European project 5G Records, applying deep learning to enhance multi-view 3D reconstruction and depth estimation for real-time novel view synthesis.

Investigating metric-scale geometry estimators and generative models (diffusion, flow matching) for depth estimation, focusing on production-ready solutions balancing reconstruction quality with real-time latency constraints.

Lecturer for Master's-level neural networks course in industrial control systems (20-30 students per semester). Develop learning materials, provide technical mentorship, and conduct tutoring sessions on deep learning theory and practical implementation.

Multi-year research collaboration (starting with Master's thesis) on deep learning techniques for volumetric video generation and 3D reconstruction in AR/VR applications. Developed novel application of diffusion models for monocular depth estimation, resulting in IEEE Access publication (RGB-D-Fusion, 2023).

Explored GAN-based domain adaptation (VoloGAN, Master's thesis 2021) to bridge quality gap between photogrammetry and mobile LiDAR depth data. Research contributed to production pipeline for single-view 3D reconstruction.

Designed FPGA-based test instrumentation (VHDL/Verilog) for high-speed digital standards including Dynamic Sequencing Generator and Analyzer (DSGA) for automated high-speed receiver testing. Developed modular high-bandwidth switching systems (up to 26.5 GHz, 8:1 configuration) and automated pre-compliance test frameworks for MIPI M-PHY and D-PHY standards.

Contributed to MIPI Alliance as member of physical layer and I3C working groups, participating in Face-to-Face meetings and interoperability plug sessions, contributing to official specifications.

Dual study program combining Bachelor's degree coursework (DHBW Horb) with professional engineering work in high-speed digital test and measurement.

Designed and validated electronic circuits. Developed C# test automation software using SCPI protocol for remote control of test instrumentation (oscilloscopes, network analyzers, signal generators) for high-speed digital receiver characterization and cable testing.