Research Engineer, AI Safety & Alignment
$225k - $400k • Remote • Redwood City, CA • FullTime
Posted 1y ago
Job Location
Redwood City, CA
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Research Engineer
About the job
Join us as a Research Engineer focused on AI safety and alignment, a critical challenge in today's AI landscape. Your work will be instrumental in understanding and mitigating the risks associated with advanced AI, conducting foundational research to enhance model safety, and solving core technical problems to ensure AI models align with human values and intentions. The Safety team pioneers techniques for more robust, honest, and harmless models. As a Research Engineer, you will translate theoretical research into practical applications, writing high-quality code to test hypotheses and integrate safety solutions into our products, contributing to user protection and the broader AI safety community.
Responsibilities
- Develop and implement novel evaluation methodologies and metrics for assessing LLM safety and alignment.
- Research and develop cutting-edge techniques for model alignment, value learning, and interpretability.
- Conduct adversarial testing to identify potential model vulnerabilities and failure modes.
- Analyze and mitigate biases, toxicity, and harmful behaviors in LLMs using methods like RLHF and fine-tuning.
- Collaborate with engineering and product teams to integrate safety research into scalable solutions.
- Stay updated on AI safety research advancements and contribute to the academic community through publications.
Requirements
- PhD (or equivalent experience) in Computer Science, Machine Learning, or a related field.
- Proficiency in writing clear and clean production-facing and training code.
- Experience working with GPUs for training, serving, and debugging.
- Experience with data pipelines and data infrastructure.
- Strong understanding of modern ML techniques, especially transformers and reinforcement learning, with a focus on safety implications.
- Passion for responsible AI development and solving complex safety challenges.