Applied AI Researcher, Benchmarking

Key Responsibilities

• Design and run evaluations for measuring model or system performance.
• Create fair, reproducible experiments and interpret empirical results.
• Develop intelligent systems using models rather than training or fine-tuning them.
• Show the power of AI in real-world applications, not just discussing future possibilities.
• Build prototypes and conduct experiments to prove the effectiveness of ideas.

Who You Are

• Have experience designing and running evaluations, including building or maintaining benchmarks, test suites, or experimental frameworks.
• Have a proven track record of research results, such as publishing in top journals, posting amazing work, or demonstrating expertise in areas like compound AI systems, agentic collaboration, and related techniques.
• Use AI tools like ChatGPT, Cursor, and Perplexity every day to accelerate your workflow.
• Have strong programming and data analysis skills to build and test prototypes of your ideas.

What We Offer

• A base salary range of $150K – $250K, depending on experience, location, and level.
• Meaningful equity and a comprehensive benefits package, including 100% coverage of medical, dental, and vision insurance for employees and dependents.
• Flexible time off, retirement and financial planning benefits, and comprehensive wellness benefits.
• Access to state-of-the-art AI models, modern AI tools, and real-world business problems.
• An ownership of high-impact projects across top enterprises in a mission-driven, fast-moving culture that values curiosity, pragmatism, and excellence.

The role is based in San Francisco and New York, with a hybrid collaboration model following a 3+ days per week (Tuesday–Thursday) in-office schedule.