Sierra
Research Intern
San Francisco, CA · On-site · Internship · Posted Oct 31, 2026
- Education
- Currently pursuing a PhD in computer science, machine learning, or a related field.
About the job
Conduct applied research to improve AI agent evaluation and behavior, using experiments on real-world interaction data and potentially translating findings into production improvements.
What you'll do
- Own a research project from question framing and experiments through paper writing and submission.
- Advance agent evaluation and study how agents reason, use tools, follow policies, and fail in multi-turn conversations.
- Explore post-training methods and analyze text and audio interaction data to improve agent behavior.
What they ask for
- Currently pursuing a PhD in computer science, machine learning, or a related field.
- Research track record, such as first-author publications or submissions at relevant venues.
- Strong experimental skills, including designing clean experiments and careful baselines.
- Fluency in Python and modern ML tooling.
Nice to have
- Research experience with LLM agents, tool use, dialogue, benchmarks, evaluation, post-training, or long-horizon optimization.
- Experience with speech, voice, or multimodal models; open-source ML research code or benchmark contributions.
Tools
Python, PyTorch, τ-bench
AI focus
Applied research on AI agents, including evaluation, reasoning, tool use, policy following, post-training, and voice AI.
Model-written summary · the original posting is authoritative