About the role#
This position supports the end-to-end validation pipeline for AI tools. You will maintain test datasets, run benchmarks, and measure agent accuracy across routing decisions, classification labels, and structured output fields. This is a contract role designed to complement your academic studies with hands-on technical work.
What you'll do#
- Run and maintain the benchmark pipeline while analyzing results to identify routing errors and regressions.
- Build and expand ground truth datasets to evaluate agent outputs.
- Identify gaps in benchmark validation and help build a more comprehensive evaluation infrastructure.
- Develop new evaluation dimensions, such as label accuracy and structured output correctness.
- Investigate failure modes in agent outputs and work with engineers to surface 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.
What you'll need#
- Current enrollment in a B.S. or M.S. program in Computer Science, Data Science, Engineering, or a related field.
- Availability for a minimum three-month assignment.
- Ability to commit to at least 20 hours per week.
- Experience with Python and familiarity with tools like Cursor or Claude.
- Understanding of evaluation concepts including precision, recall, F1 score, and confusion matrices.
- Comfort working with structured data formats like CSV and JSON.
- Experience writing or modifying reproducible analysis scripts.
- Prior exposure to LLM-based systems, prompt engineering, or AI agent evaluation is a plus.
- Familiarity with Jira or Slack.
- Ability to work on-site and adhere to strict confidentiality requirements.
Location & details#
- Location: Foster City, California.
- Work Modality: Hybrid or on-site.
- Compensation: $30 per hour.
- Employment Type: Contract position.
About Zoox
Zoox develops autonomous, purpose-built vehicles for mobility-as-a-service. The company focuses on robotics, artificial intelligence, and electric vehicle technology. Founded in 2014, it maintains its headquarters in Foster City, California. The organization employs nearly 4,800 people.
How to get in at Zoox
Applying early to Zoox provides a distinct advantage because recruiters review applications before the volume of candidates becomes unmanageable. Intern Insider sends an instant alert the moment a role matching your target is published anywhere, ensuring you can submit your materials among the first. This timing often determines whether your resume reaches a human reader or stays in the queue. You can also improve your response rates by reaching out to the recruiters behind these roles directly to ask about the position or a referral. Intern Insider surfaces the contact information for these hiring professionals, allowing you to bypass the standard portal and introduce yourself to the people actually making the decisions.
