ML Research Engineer — LLM Safety
Skills
Computer ScienceArt ResearchArtificial IntelligenceBenchmarkingEasily AdaptableLarge Language ModelsMachine Learning
What the job involves
The main requirements, responsibilities and hiring steps.
Requirements
- Deep domain knowledge in LLM safety techniques
- Extensive experience in designing training and implementing multiple different types of LLM models and architectures in the real world
- Comfortability with leading end-to-end projects
- Adaptability and flexibility to learn implement and extend state-of-the-art research
- Preferred past research or projects in either attacking or defending LLMs
Day to day
- Own an LLM vertical with a focus on a specific safety domain, technique, or use case either from defense or red-team attack perspective
- Generate high quality synthetic data train LLMs and conduct rigorous benchmarking
- Deliver robust scalable and reproducible production code
- Push the envelope by developing novel techniques and research that delivers the world’s most harmless and helpful models
- Co-author papers patents and presentations with our research team by integrating other members’ work with your vertical