Part-Time Student Worker – AI Validation and Benchmarking Engineer

Zoox•Foster City, CA

4d•Onsite

About The Position

Zoox is an autonomous ride-hailing company building the world's first purpose-built robotaxi — fully electric, bidirectional, with no steering wheel or driver's seat. Backed by Amazon and founded to make transportation safer, cleaner, and more accessible, Zoox designs its vehicles entirely around the rider. We're currently operating in Las Vegas and San Francisco, with Austin and Miami on the horizon, and testing underway across seven U.S. markets. This role requires supporting the end-to-end validation pipeline for AI tools: maintaining test datasets, running benchmarks, and measuring agent accuracy across routing decisions, classification labels, and structured output fields.

Requirements

Currently enrolled in a B.S. or M.S. in Computer Science, Data Science, Engineering or a related field
Available to commit to a minimum three-month assignment
Able to commit to a minimum of 20 hours per week
Able to work on-site at one of our office locations
Must adhere with Zoox confidentiality requirements, including refraining from using or sharing proprietary company information outside of Zoox, such as in academic research, theses, publications, or presentations
Familiar with Cursor or Claude
Familiar with Python
Familiar with evaluation concepts: precision, recall, F1 score, and confusion matrices
Comfortable working with structured data (CSV, JSON)
Experience modifying or writing reproducible analysis scripts

Nice To Haves

Prior exposure to LLM-based systems, prompt engineering, or AI agent evaluation
Experience with Jira or Slack (e.g. ticketing systems, messaging apps)

Responsibilities

Run and maintain the benchmark pipeline, analyzing results to identify routing errors and regressions across agent variants
Build and expand ground truth datasets used to evaluate agent outputs against known-correct answers
Identify and address gaps in benchmark validation and support building a more comprehensive evaluation infrastructure to improve validation prior to release
Develop new evaluation dimensions such as label accuracy and structured output correctness beyond the existing team classification benchmarks
Investigate failure modes in agent outputs and work with engineers to surface actionable improvements
Write scripts and tooling to automate data collection, result parsing, and metric reporting
Document findings, track benchmark trends over time, and present results to the team