Research Scientist

Skills

About the Role

You will lead a research agenda on LLM evaluation, model quality, routing optimization, and AI usage patterns. You will design benchmarks, conduct empirical studies, develop statistical routing foundations, collaborate with external researchers, and translate findings into platform improvements.

Requirements

• MS or PhD in a quantitative field
• Track record of original research through first-author publications, open-source contributions, or equivalent industry impact
• Expertise in statistics, experimental design, and causal inference
• Strong Python programming skills
• SQL proficiency for large-scale analytical databases
• Experience with modern machine learning and natural language processing techniques
• Knowledge of LLM evaluation, fine-tuning, embeddings, classification, or reinforcement learning from human feedback
• Familiarity with model architectures, provider ecosystems, benchmark suites, and leading-model limitations
• Ability to communicate complex findings clearly

Responsibilities

• Own a research agenda on LLM evaluation, model quality, routing optimization, and AI usage patterns
• Design novel evaluation frameworks and benchmarks
• Conduct large-scale empirical studies of LLM behavior
• Develop statistical and mathematical foundations for routing systems
• Identify product applications for research findings
• Collaborate with external researchers, model providers, and the open-source community
• Translate research findings into platform improvements

Benefits

• Equity