18 hours ago
Responsibilities
- Run and maintain benchmark pipelines and analyze results for routing errors and regressions across agent variants.
- Build and expand ground-truth datasets for evaluating agent outputs against known-correct answers.
- Identify validation gaps and support development of comprehensive evaluation infrastructure before release.
- Develop evaluation dimensions for label accuracy and structured-output correctness.
- Investigate agent-output failure modes and collaborate with engineers on actionable improvements.
- Write scripts and tooling to automate data collection, result parsing, and metric reporting.
- Document findings, track benchmark trends, and present results to the team.
Requirements
- Currently enrolled in a B.S. or M.S. program in Computer Science, Data Science, Engineering, or a related field.
- Available for a minimum three-month assignment and at least 20 hours per week.
- Able to work onsite at one of the company’s office locations.
- Familiarity with Cursor or Claude and Python.
- Familiarity with precision, recall, F1 score, and confusion matrices.
- Comfort working with CSV and JSON structured data.
- Experience modifying or writing reproducible analysis scripts.
- Must comply with Zoox confidentiality requirements and not share proprietary information externally.
Benefits
- Contract position through a vendor with a compensation rate of $30/hour; benefits eligibility is determined by the vendor.
- Minimum three-month assignment with at least 20 hours per week.
- Onsite work at one of Zoox’s office locations.
- Hands-on experience contributing to real AI validation projects alongside engineers and researchers.
- This is a student worker role rather than an internship, with no structured intern programming or guaranteed full-time pathway.
Tech Stack
Categories
About Zoox
Zoox builds a fully autonomous, purpose-built electric vehicle and the end-to-end platform to operate it as an urban robotaxi service. The company designs the vehicle, self-driving software, and fleet operations in-house to offer mobility-as-a-service rather than selling cars. Founded in 2014 and headquartered in Foster City, California, Zoox is a subsidiary of Amazon.