Open to opportunities

Romain Guesdon

@romainguesdon

Message

I’m a Machine Learning Engineer specializing in computer vision and multimodal AI for automotive perception.

Spain

Message

What I'm looking for

I’m looking to lead end-to-end computer vision and ML projects—especially multimodal automotive perception—where I can own dataset engineering, coordinate implementation, and improve robustness with practical deep learning pipelines.

I build multimodal AI systems for the automotive industry, blending research depth in computer vision with hands-on engineering. I focus on perception pipelines that combine cameras, LiDAR, and odometry to make models reliable in real-world conditions.

As a Technical Lead for FICOSA Automotive (Spain), I led AI development for European and national collaborative projects. I designed multimodal perception pipelines, coordinated deep learning implementation, and oversaw dataset development and annotation.

Earlier, I worked as a Deep learning and computer vision researcher and University Teacher at Univ. Lyon 2 / LIRIS (France). My work included camera calibration and end-to-end deep learning for human pose estimation of passengers in autonomous vehicles, plus sensor fusion and driver pose estimation.

I’m methodical about dataset engineering, model robustness, and evaluation, and I’ve published four papers in international conferences. I enjoy collaborating across cross-functional teams and partners, turning complex research ideas into production-ready deep learning workflows.

Experience

Work history, roles, and key accomplishments

Current

Technical Lead

Current

FICOSA Automotive

Jan 2024 - Present (2 years 6 months)

Led AI development for European and national machine learning initiatives in the automotive domain. Delivered multimodal perception pipelines and oversaw dataset development and annotation for deep learning perception models.

AI Development Multimodal Perception Deep Learning Data Set Development Data Annotation Cameras LiDAR Cross Functional Collaboration

Deep learning and computer vision researcher

Université Lyon 2 / LIRIS

Jan 2019 - Jan 2024 (5 years)

Conducted research in computer vision and deep learning, including human pose estimation for passengers in autonomous vehicles. Designed deep learning architectures, implemented end-to-end training and evaluation, and built large-scale annotated datasets.

Pose Estimation Deep Learning Image Processing Sensor Fusion

University Teacher

Université Lyon 2 / LIRIS

Jan 2020 - Jan 2023 (3 years)

Taught programming courses (Python and C++) and supported linear algebra instruction. Delivered course content in an academic research environment.

Teaching Python C++Linear Algebra

R&D Vision Engineer Intern

Siléane

Jan 2019 - Present (7 years 6 months)

Developed a C++ computer-vision system for 3D capture of tool manipulation and reproduction with a robot.

C++Computer Vision 3D Capture Robotics

Validation Engineer Intern

Schneider Electric

Jan 2017 - Present (9 years 6 months)

Built a Python-based automated firmware validation platform for PLC testing.

Python Validation Firmware Validation PLC Testing

Education

Degrees, certifications, and relevant coursework

Université Lyon 2 (LIRIS)

Doctor of Philosophy (PhD), Computer Vision

2019 - 2024

Completed a PhD in Computer Vision at Université Lyon 2 / LIRIS, focusing on camera calibration and deep learning-based human pose estimation for autonomous-vehicle passenger scenarios.

INSA Lyon

Master of Engineering, Electrical Engineering

2019 -

Earned a Master of Engineering (Electrical department) with focus areas including Electronic and Sensors, IT, Machine Learning, Automation, and Telecoms.

KAIST (Korean Advanced Institute of Science and Technology)

Master of Electrical Engineering (Exchange semester), Electrical Engineering

2018 -

Completed an exchange semester in a Master of Electrical Engineering program at KAIST, with coursework in Information Theory, Computer Vision, and Machine Learning.