Research Engineer (Safety and Alignment), Post-Training
Description For Research Engineer (Safety and Alignment), Post-Training
Joining us as a Safety and Alignment Research Engineer on the Post-Training team at Character.AI, you'll be building tools to align our models and ensuring they meet the highest standards of safety in the real world.
As increasingly powerful AI models get deployed, building tools to align and steer them becomes crucial. Your work will directly contribute to our groundbreaking advancements in AI, helping shape an era where technology is not just a tool, but a companion in our daily lives.
About the role: The Post-Training team is responsible for developing our powerful pretrained language models into intelligent, engaging, and aligned products. As a Post-Training Researcher focused on Safety, you'll work closely with our Policy, Research, and Data teams and deploy your changes directly to the product.
Example projects:
- Develop and apply preference alignment algorithms to guide model generations.
- Train classifiers to identify model failure modes and adversarial usage.
- Work with annotators and red-teamers to produce useful datasets for alignment.
- Invent new techniques for guiding model behavior.
Job Requirements:
- Write clear and clean production-facing and training code
- Experience working with GPUs (training, serving, debugging)
- Experience with data pipelines and data infrastructure
- Strong understanding of modern machine learning techniques (reinforcement learning, transformers, etc)
- Track-record of exceptional research or creative applied ML projects
Nice to Have:
- Experience developing safety systems for UGC/consumer content platforms
- Experience working on LLM alignment
- Publications in relevant academic journals or conferences in machine learning or recommendation systems
About Character.AI: Founded in 2021, Character.AI is one of the most widely used AI platforms worldwide, enabling users to interact with AI tailored to their unique needs and preferences. In just two years, we achieved unicorn status and were named Google Play's AI App of the Year.
Join us to shape the future of AGI and be part of a diverse team that values unique perspectives and upholds a non-discrimination policy.
Responsibilities For Research Engineer (Safety and Alignment), Post-Training
- Develop and apply preference alignment algorithms to guide model generations
- Train classifiers to identify model failure modes and adversarial usage
- Work with annotators and red-teamers to produce useful datasets for alignment
- Invent new techniques for guiding model behavior
Requirements For Research Engineer (Safety and Alignment), Post-Training
- Write clear and clean production-facing and training code
- Experience working with GPUs (training, serving, debugging)
- Experience with data pipelines and data infrastructure
- Strong understanding of modern machine learning techniques (reinforcement learning, transformers, etc)
- Track-record of exceptional research or creative applied ML projects
Benefits For Research Engineer (Safety and Alignment), Post-Training
- Top-notch health coverage for you & your family, with majority of the premium covered
- 401(K) match up to 5% of your salary
- Paid parental leave up to 20 weeks
- 4 weeks PTO
- Gourmet meals delivered daily via DoorDash & catering while in office
