Senior AI/ML Engineer & Researcher
Diffusion Models · Robotics · World Models · Physical AI
Building the bridge from diffusion policy research to production robot deployment. Direct NVIDIA Cosmos Policy collaborator. First-author at AAMAS 2026. Leading a 10+ person R&D team at idealworks (BMW Group).
I am a Senior AI/ML Engineer at idealworks GmbH in Munich, building the bridge between cutting-edge ML research and production robot systems.
My current work centers on Diffusion Policy and Vision-Language-Action models. I collaborate directly with NVIDIA on Cosmos Policy, building diffusion-based policy learning for embodied AI. My first-author paper SPADE (AAMAS 2026) extends the foundational Diffusion Policy work by Chi et al. into multi-agent robotic path planning.
What sets me apart: I don't just publish — I deploy. My systems run on real robots in BMW production facilities. I've led a team of 10+ engineers and researchers, mentored Master's students to publication, and built everything from production Visual SLAM to large-scale synthetic data pipelines with NVIDIA Cosmos.
I hold an M2 in Mathematics, Machine Vision and Machine Learning from École Normale Supérieure Paris-Saclay, one of France's most selective Grandes Écoles.
idealworks GmbH
inmind.ai
BMW Group / idealworks GmbH
École Normale Supérieure Paris-Saclay
Université Paris-Saclay
Holy Spirit University of Kaslik (USEK)
Direct collaboration with NVIDIA to fine-tune and integrate NVIDIA Cosmos data generation and augmentation pipeline into the AMR domain and modalities. Developing Synthetic Data Generation pipeline at scale for production use-cases. Tools used include Grafana, Prometheus, LakeFS, Determined AI for GPU inference job orchestration, FastAPI for API development, and Docker for containerization.
NVIDIA Cosmos Webpage→Designed and deployed a hybrid LiDAR + Visual SLAM system transitioning from localization fallback to primary production system for autonomous mobile robots in warehouse environments.
Built and deployed a modular people anonymization pipeline for autonomous mobile robots in production. The pipeline support modular model support with automatic benchmarking and selection. Deployed on-site and on AWS with Lambda, EC2, Batch and S3. CI/CD with Github Actions. On-site deployment uses Docker and Celery for distributed processing.
Built and deployed a robot motion prediction pipeline on-edge on NVIDIA Jetson Xavier device for on-edge collision avoidance in production. Technologies for the core were a YOLO model for object detection and an Unscented Kalman Filter for motion estimation and tracking. Deployment was done using ROS, Docker, ONNX and TensorRT.
Built sim-to-real data pipelines using Unity, NVIDIA Isaac SIM, and NVIDIA Cosmos for training perception and prediction models with efficient transfer learning.
Targeting ECCV 2026 · Second Author
Applying NeRF for robust localization in changing and degrading environments.
Extended Abstract · First Author
Extends diffusion policy and imitation learning to path planning for autonomous multi-agent systems. Builds upon Chi et al. (RSS 2023).
IEEE IPAS · Second Author
Introduces sketch-guided imitation learning for AMR path planning, enabling non-technical users to draw desired navigation paths on 2D maps. Uses U-net models with a novel evaluation framework combining image generation and robotics metrics.
Open-source work and research implementations. View all repositories on GitHub.
End-to-end Sketch-Guided Path Planning through Imitation Learning for Autonomous Mobile Robots
A novel approach for autonomous robot navigation that uses hand-drawn sketches as high-level guidance for path planning. The system bridges human intent with robotic execution through imitation learning.
Semantic segmentation for autonomous robot navigation in urban environments
Pixel-level semantic segmentation enabling robots to identify safe sidewalk areas from RGB camera feeds. Complete pipeline from data labeling through training to real-time inference with a custom 276-image dataset.
Multi-Agent Reinforcement Learning benchmarking for decentralized autonomous driving
Benchmarking suite for evaluating decentralized multi-agent RL algorithms in high-density autonomous driving scenarios using highway-env simulation.
GANs for data augmentation and image-to-image translation
Tackling data scarcity through GAN-based synthetic image generation and CycleGAN for unpaired image-to-image translation across visual domains.
Regression analysis for predicting professional athlete market values
End-to-end ML project predicting football player transfer values. Demonstrates reproducible ML workflows with DVC for experiment tracking and Dockerized execution.
Healthcare analytics: classification model for stroke risk prediction
Classification project for predicting stroke risk using patient health data. Covers EDA, class imbalance handling, and multi-classifier comparison.
Utility scripts for verifying GPU acceleration across TensorFlow 2 and PyTorch environments.
View on GitHubCustomized Neovim configuration built on AstroNvim, optimized for Python, C++, and CUDA development.
View on GitHubData and model version control using DVC in MLOps — setup guides, remote storage, and Python API integration.
View on GitHubProfessional LaTeX templates for academic publications and conference papers (IEEE format presets).
View on GitHub