Research Intern
Sierra · San Francisco, CA
About this role
## Research Intern ### About Sierra Sierra is the leading platform for customer-facing AI agents, partnering with major brands including The GAP, Rocket Mortgage, SoFi, Sutter Health, and SoftBank to transform how they serve customers and grow their businesses. Sierra is primarily an in-person company based in San Francisco, with growing offices across North America, Europe, and Asia. Our values—**Trust**, **Customer Obsession**, **Craftsmanship**, **Intensity**, and a commitment to balancing **Family**—guide how we work. Sierra’s **Applied Research** team builds better, faster, and more cost-effective models behind our agents. Work includes post-training open-weight models for specialized capabilities, new approaches to voice AI, and benchmarks used to measure agents (including **τ-bench**). ### What You’ll Do - **Own a research project** end-to-end: frame the question, run experiments, and write/submit a paper. - **Advance agent evaluation**, e.g., extend **τ-bench** to new domains/modalities/long-horizon tasks, or build new ways to measure reliability and consistency. - **Study agent behavior** in multi-turn conversations: how agents reason, use tools, and follow policies—and where/why they fail. - **Explore post-training methods** such as supervised fine-tuning and reinforcement learning; measure improvements rigorously. - **Work with large-scale datasets** of text and audio interactions to ensure research is grounded in real customer problems. - Collaborate with researchers and engineers; when it makes sense, **turn findings into production improvements**. ### What You’ll Bring - Currently pursuing a **PhD** in computer science, machine learning, or a related field. - A **research track record**, such as first-author publications or submissions to venues like **NeurIPS, ICML, ICLR, ACL, EMNLP, Interspeech,** or **ICASSP**. - Strong **experimental skills**: design clean experiments, build careful baselines, and be candid about results. - Fluency in **Python** and modern ML tooling (e.g., **PyTorch**, and LLM inference/training stacks). - **High agency** and a builder’s mindset—able to work across the stack to get experiments running. - Clear communication and strong collaboration skills.
Listing freshness
CronJobs last confirmed this listing 10h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.