Niantic Spatial
AI Automation Engineer, Real-World Test Lab
$158K–$210K
San Francisco, CA · Hybrid · Full-time · Posted Sep 29, 2026
- Education
- Bachelor's degree in a relevant field, or equivalent experience.
About the job
Build and operate end-to-end automated evaluation systems that test spatial AI workflows across releases and produce reproducible, comparable evidence and diagnostics.
What you'll do
- Automate evaluation runs, including environment setup, orchestration, artifact capture, and result collection.
- Create comparable scorecards and actionable, reproducible diagnostics across versions, devices, and capture conditions.
- Turn recurring evaluations into release-triggered protocols and automate agent-driven workflows where appropriate.
What they ask for
- Built and maintained production-grade automation or test infrastructure used by other engineers.
- Evaluated systems with graded correctness, such as quality, accuracy, or latency thresholds.
- Strong Python skills and fluency in orchestration, CI-style pipelines, cloud storage, and reproducible environments.
- Integrated with backend services and APIs owned by other teams.
Nice to have
- Built agent-based or LLM-driven automation for tasks previously requiring human judgment.
- Worked on evaluation or benchmarking for computer vision, 3D reconstruction, or spatial systems.
Pay
$158,400 to $210,000 per year (base salary); $158.4K – $210K (compensation; type not specified)
Tools
Python
AI focus
Automate evaluation of physical and spatial AI systems, including agent workflows for customer use cases; assess where agents can and cannot replace human judgment.
Model-written summary · the original posting is authoritative