Position postdoc sur l'alignement de l'IA et l'IA sûre disponible à l'EPFL DLAB — EPFL
NouveauCHF 60 500 - 91 500
EPFL · Lausanne (VD)
- Lieu
- Lausanne
- Contrat
- full-time
- Publié
- il y a 5 jours
SalaireCHF 60 500 - 91 500
Vue d’ensemble du poste
Mission Research topics: Alignment Large language models Natural language processing
- Mission Research topics: Alignment Large language models Natural language processing
- To this end, you will combine synthetic data generation, mechanistic interpretability, LLM pre- and posttraining, and model evaluation in novel ways. Principales tâches et responsabilités
Responsabilités principales
- To this end, you will combine synthetic data generation, mechanistic interpretability, LLM pre- and posttraining, and model evaluation in novel ways. Principales tâches et responsabilités
Processus de candidature
- Mechanistic interpretability Applications are invited for a postdoctoral position at EPFL, to be hosted by the Data Science & AI Lab , headed by Prof.
- Robert West.
- We seek a candidate who will lead ground-breaking research projects with the goal of building safe AI that truly cares about human interests.
- Instead of viewing alignment as mere postprocessing of pretrained models (“lipstick-on-a-pig alignment”), you will contribute to our agenda of “raising” models that will be continuously aligned throughout the training process, starting from token 1 in pretraining (see here for a high-level vision).
- You will contribute to the Swiss AI Initiative , in particular by incorporating your research results into Apertus , SwissAI’s open, transparent, multilingual language model.
- You will work in a stimulating, open, and international research environment consisting of many highly talented and motivated students, embedded in a strong network of academic and industrial collaborators.
- Other benefits include a competitive salary (starting at around CHF 88,000 p.a.), an extremely well funded national research system, an office next to a stunning lake and even more stunning mountains, and generous travel support.
- Involvement in teaching is possible but not required.
Contacts
- For any further information, please contact: [email protected] Contract Start Date : 01/04/2026 Activity Rate Min : 100.00 Activity Rate Max : 100.00 Contract Type: CDD Duration: 1 year Reference: 2077
Détails supplémentaires
- details for 3 referees. Mission Research topics: Large language models Natural language processing
- To this end, you will combine synthetic data generation, mechanistic interpretability, LLM pre- and posttraining, and model evaluation in novel ways. Principales tâches et responsabilités
- Project work with MS and PhD students is expected.
- Strong programming skills and experience with machine learning frameworks are required. A stimulating and international working environment
- Informations Only applications submitted through the online platform are considered. You are asked to supply: A brief cover letter (pdf, up to 2 pages). A CV with a publication list. A research statement (pdf, up to 3 pages).
- Contact details for 3 referees.
Notes et contenu original
- Mission Research topics:
- Large language models
- Natural language processing
- To this end, you will combine synthetic data generation, mechanistic interpretability, LLM pre- and posttraining, and model evaluation in novel ways.
- Principales tâches et responsabilités
- Strong programming skills and experience with machine learning frameworks are required.
- Nous offrons
- A stimulating and international working environment
- Informations Only applications submitted through the online platform are considered.
- You are asked to supply:
