Projects
Projects
Second Order Jailbreak
NeurIPS 2023
Dec 2023
We authored a paper on Second Order Jailbreak where we delved into the risks posed by malignant intelligent actors spreading their influence over networks of agents with varying intelligence and motivations. We run experiments on a multi-agent environment available here. You can see all the different conversations the agents had with each other on our playground website. We've presented our work at NeurIPS 2023. The current version of the paper can be found here. We are currently working on a follow-up paper, which will include a more detailed analysis of the risks and the strategies that can be used to mitigate them.
Co-Creator and Vice President
Safe AI Lausanne Group
Jan 2023 - Now
Co-created and leading a volunteer-driven organization focused on AI safety and alignment, organizing talks, round tables, seminars and bootcamps to foster knowledge exchange and raise awareness about AI risks. During which I:
- Successfully led the AI Safety Fundamentals from BlueDot Impact, implementing the AI Alignment Curriculum.
- Organized a 2-week AI Safety bootcamp in Sep. 2023, aiming to skill up 20 motivated participants and encourage them to work in the field of AI Safety. Delivered in-depth training on the technical aspects of Transformer architecture, including mechanistic interpretability (Induction and Indirect Object Identification circuits) and provided lessons on RL, RLHF and jailbreaking of LLMs.
Experience
Experience
Data Officer
NCCR Catalysis (EPFL/ETHZ)
Jan 2023 - Now
In my role as a Data Officer at NCCR Catalysis (EPFL/ETHZ), I collaborate with numerous labs across Switzerland to standardize practices and optimize data management. I am developing a technique for uniform catalyst storage and sharing, and facilitating open science through AI model platforms. Additionally, I am co-authoring a manuscript detailing our research on ML-based detection of metallic atoms in microscope images and in the process of publish a second publication that will enable researchers to label microscope images seamlessly
Fullstack software engineer
Graux Guitar Loops
Jul 2022 - Now
Created and launched SpicyX, a streaming platform for guitar loops. Leveraged NextJS, MongoDB, and Vercel to build a scalable platform, attracting over 100+ monthly subscribed producers.
Teaching Assistant
École Polytechnique de Louvain
Sep 2020 - Jun 2021
Gave practice sessions to students (between 20 and 50 per session) for the following courses:
- Algorithms and data structures
- Discrete math and probability
- Numerical methods
- Signals and systems
- Python
Computer Vision Internship
Aerospacelab
Jul 2020 - Sep 2020
Developed and deployed a Mask-RCNN model for satellite image analysis, encompassing detection, segmentation, and area computation. Integrated the model with location information obtained from OpenStreetMap for accurate image matching. The model is currently in production.
Education
Education
M.S. Data Science Engineering
École Polytechnique Fédérale de Lausanne
Sep 2021 - Sep 2022
One year exchange at EPFL, where I undertook a master thesis titled "Point cloud compression for DNA based storage" and achieved a grade of 5.75/6. This research involved building an end-to-end point cloud compressor for quaternary based coding while adhering to DNA sequencing, storage, and synthesis constraints. In addition to my thesis, I completed the courses Cryptography and security, Information security and privacy, Decentralized systems and Seminar in advanced topics in machine learning. Took part in the Effective Altruism Lausanne and GNU Generation associations.
M.S. Data Science Engineering
École Polytechnique de Louvain
Sep 2020 - Sep 2022
Master degree in data science with a specialization in cryptography and computer systems. Grade: Cum Laude.
B. Sc. Engineering
École Polytechnique de Louvain
Sep 2017 - Sep 2020
Bachelor degree in engineering with a specialization in applied mathematics and computer science. Grade: Cum Laude.