Alejandro Aristizábal
AI Safety Researcher·Machine Learning Engineer
ML Engineer and AI Safety Researcher with 6+ years in deep and reinforcement learning. Currently a Researcher at Arcadia Impact's Alignment Team (in collaboration with the UK AI Security Institute), studying automated alignment research.
Previously completed LASR Labs, where I worked on Unexploitable Search as part of their AI safety research programme. Co-author of the MedPerf platform, published in Nature Machine Intelligence, enabling federated benchmarking of medical AI.
Writing
Publications
- 2026 The 2024 Brain Tumor Segmentation Challenge Meningioma Radiotherapy (BraTS-MEN-RT) dataset. Scientific Data. doi
- 2025 Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge. Nature Communications. doi
- 2025 FeTS 2.0: Federated learning sets benchmark in post-op GBM segmentation. Neuro-Oncology. doi
- 2025 The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI. ML for Biomedical Imaging. doi
- 2025 Analysis of the MICCAI Brain Tumor Segmentation — Metastases (BraTS-METS) 2025 Lighthouse Challenge. arXiv
- 2024 BraTS-PEDs: Results of the Multi-Consortium International Pediatric Brain Tumor Segmentation Challenge 2023. ML for Biomedical Imaging. arXiv
- 2024 Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge. ML for Biomedical Imaging. arXiv
- 2024 Analysis of the 2024 BraTS Meningioma Radiotherapy Planning Automated Segmentation Challenge. arXiv
- 2023 Federated benchmarking of medical artificial intelligence with MedPerf. Nature Machine Intelligence. doi arXiv
- 2023 The Brain Tumor Segmentation (BraTS) Challenge: Local Synthesis of Healthy Brain Tissue via Inpainting. arXiv
- 2019 Diagnosis evaluation of the coffee leaf rust development stage in the Colombian Caturra variety integrating remote sensing, wireless sensor networks and deep learning.