character logocharacter logo

Research Engineer in AI Safety & Alignment

characterRedwood City, CA
On-site Full-time

Clicking Apply Now takes you to AutoApply where you can tailor your resume and apply.


Experience Level

Experience

Qualifications

What You'll DoDesign and implement innovative evaluation methodologies and metrics to measure the safety and alignment of large language models. Conduct research and develop state-of-the-art techniques for model alignment, value learning, and interpretability. Perform adversarial testing to identify potential vulnerabilities and failure modes within our models. Examine and reduce biases, toxicity, and other detrimental behaviors in large language models utilizing methods like reinforcement learning from human feedback (RLHF) and fine-tuning. Collaborate with engineering and product teams to translate safety research into effective, scalable solutions and best practices. Keep updated with the latest advancements in AI safety research and engage with the academic community through publications and presentations.

About the job

About the Role and Team

As a Research Engineer at Character, you will play a critical role in addressing one of the most pressing challenges in artificial intelligence: ensuring safety and alignment. Your contributions will be vital in identifying and mitigating the risks associated with advanced AI systems, conducting essential research to enhance the safety of our models, and tackling fundamental technical challenges related to AI alignment, ensuring our models align with human values and intentions.

The Safety team is committed to innovating and applying techniques that enhance the robustness, honesty, and harmlessness of our models. In this position, you will connect theoretical research with practical applications, producing high-quality code to test hypotheses and directly integrating effective safety solutions into our products. Your research will safeguard millions of users while advancing the scientific community's understanding of how to create safe and beneficial AI.

About character

Character is at the forefront of AI innovation, dedicated to developing responsible and safe artificial intelligence solutions. Our team of experts works tirelessly to align advanced AI technologies with human values, ensuring that our models contribute positively to society.

Similar jobs

Browse all companies, explore by city & role, or SEO search pages. View directory listings: all jobs, search results, location & role pages.

Tailoring 0 resumes

We'll move completed jobs to Ready to Apply automatically.