Research Engineer, Agentic AI Evals

HUD (YC W25) is an innovative AI company developing comprehensive evaluation tools for Computer Use Agents (CUAs) that browse the web. As a YC-backed startup with $2 million in seed funding, they're experiencing strong demand and rapid growth. The Research Engineer role focuses on building and implementing evaluation frameworks for AI agents, combining technical expertise with research capabilities.

The position offers a unique opportunity to work with a distinguished team including international Olympiad medallists and researchers published in prestigious conferences like ICLR and NeurIPS. The role involves creating evaluation environments, developing datasets, and contributing to the advancement of AI agent assessment methodologies.

This is an ideal position for someone passionate about AI evaluation and safety, with strong technical skills in Python and web technologies. The company offers flexibility in work arrangements, with both remote and office options in San Francisco or Singapore. They value technical aptitude and learning potential over years of experience, making it an excellent opportunity for motivated engineers interested in AI safety and evaluation.

The role combines practical engineering with research aspects, requiring both technical proficiency and understanding of AI systems. Working at HUD means joining a fast-growing team of about 15 people, with the opportunity to make significant contributions to the field of AI evaluation. The company provides comprehensive support for relocation and visas for strong candidates, demonstrating their commitment to building the best possible team.

The position would be particularly appealing for engineers who enjoy building evaluation systems, have experience with LLM frameworks, and are interested in contributing to AI safety and alignment. The work environment emphasizes both quality and quantity in contributions, with concrete goals like creating multiple evaluation environments daily.