Staff AI Research Scientist - Evaluation - Remote

Overview

As a Staff Research Scientist at Handshake AI, you will drive frontier research on AI evaluation methodologies, focusing on large language models and their interactions with human knowledge.

In Short

• Lead teams in original research on LLM evaluation and interpretability.
• Develop frameworks to assess model capabilities and limitations.
• Collaborate with engineers to create scalable evaluation systems.
• Pioneer methods for measuring reasoning and trustworthiness in AI.
• Author code for large-scale experimentation and evaluation workflows.
• Publish research in top-tier venues.
• Work cross-functionally to set industry standards for AI evaluation.

Requirements

• PhD or equivalent in machine learning, computer science, or related fields.
• 6+ years of experience in a research-first environment.
• Strong background in LLM research and evaluation methodologies.
• Proven ability to design and execute evaluation research.
• Proficiency in Python and PyTorch for model analysis.
• Experience in benchmark development and systematic assessment.
• Strong publication record in evaluation or interpretability.
• Ability to communicate complex insights clearly.

Benefits

• Equity in a fast-growing company.
• 401(k) match and competitive compensation.
• Paid parental leave and fertility benefits.
• Medical, dental, vision, and mental health support.
• $2,000 learning stipend for ongoing development.
• Flexible PTO and holidays.
• Stipends for home office setup and commuting.