Applied AI Researcher, Agent Systems Evaluation

📋 Description

• Role focuses on evaluating AI agent systems, end-to-end evaluation pipelines, and closed-loop
• Own the evaluation pipeline end to end: data collection, loop construction, and automated hill
• Work with frontier models and open-weight vision-language models, performing supervised fine-tuning

🎯 Requirements

• Graduate degree in CS/ML or equivalent research experience; strong research judgment.
• Deep understanding of LLMs, post-training, RL, and evaluation pipelines for AI systems.
• Hands-on experience with Python and production systems; ability to run experiments end-to-end.
• Experience with agent systems, evaluation harnesses, task suites, or LLM-as-judge systems; comfort

🎁 Benefits

• Competitive base pay with annual bonus, equity, and comprehensive benefits.
• Opportunity to impact hundreds of engineers; work directly with leadership and CEO.
• Hybrid environment with direct access to compute and production data.