Research Engineer / Research Scientist, Alignment (AI)

TL;DR

Research Engineer / Research Scientist, Alignment (AI): Designing and implementing scalable solutions to ensure AI systems align with human intent in complex scenarios with an accent on developing methodologies for robust human oversight. Focus on evaluating alignment capabilities and creating innovative human-AI interaction paradigms.

Location: Hybrid (3 days in the office per week, San Francisco, CA)

Company

hirify.global is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Develop and evaluate alignment capabilities that are subjective and context-dependent.
• Design evaluations to measure risks and alignment with human intent.
• Build tools to study and test model robustness.
• Design experiments to understand how alignment scales with resources.
• Develop new Human-AI interaction paradigms.
• Train models to be calibrated on correctness and risk.

Requirements

• PhD or equivalent experience in relevant fields.
• Strong engineering skills in large-scale machine learning systems (e.g., PyTorch).
• Deep understanding of alignment algorithms.
• Experience in developing data visualization or collection interfaces (e.g., TypeScript, Python).
• Ability to thrive in fast-paced, collaborative research environments.