Perplexity AI · San Francisco +1 · Remote · Apr 13
Build shared eval infrastructure guiding product and model decisions at scale.
$200k–$350k
EvaluationsSafety and Alignment · SAF
Evaluations
Test models before they reach users.
- Build capability and safety evals
- Run pre-deployment test suites
- Report results to decision-makers
48 open42 of 48 list compensation: $30k–$525k
48 open roles
Waymo · San Francisco, California, United States +1 · Onsite · Sep 23
Build state-of-the-art evaluation tools for simulator realism via ML modeling.
$146k–$177k
EvaluationsWaymo · Mountain View, CA, USA +1 · Onsite · Apr 17
Build scalable ML systems to evaluate interesting driving behaviors.
$213k–$263k
EvaluationsWaymo · Mountain View, CA, USA; San Francisco, CA, USA +2 · Onsite · Dec 2025
Measure and improve quality of software driving autonomous vehicles.
$204k–$259k
EvaluationsWaymo · Mountain View, CA, USA +1 · Onsite · Oct 2
Improve quality and reliability of large-scale perception evaluation workflows.
$146k–$177k
EvaluationsWaymo · Mountain View, CA, USA; New York, NY, USA +1 · Onsite · Dec 2025
Build rich metrics to understand Waymo Driver behavior in the real world.
$238k–$302k
EvaluationsWaymo · Mountain View, California, USA +1 · Onsite · Sep 21
Build automated pipelines turning large-scale simulation logs into structured graphs.
$146k–$177k
EvaluationsWaymo · San Francisco, CA, USA; Mountain View, CA, USA +2 · Onsite · Oct 6
Measure and improve the quality of software that drives the car.
$251k–$310k
EvaluationsWaymo · Mountain View, CA, USA; San Francisco, CA, USA; New York, NY, USA +3 · Onsite · Oct 2
Improve evaluation pipelines to deliver stronger signals with fewer resources.
$213k–$263k
EvaluationsWaymo · San Francisco, CA, USA; Mountain View, CA, USA +2 · Onsite · Sep 10
Build ML models that auto-generate HD maps from raw sensor streams.
$213k–$263k
EvaluationsWaymo · Mountain View, California, United States; San Francisco, California, United States; New York City, New York, United States. +3 · Onsite · Dec 2025
Build tools to mine novel safety-critical situations from driving logs.
$281k–$356k
EvaluationsWaymo · Mountain View, CA, USA; San Francisco, CA, USA +2 · Onsite · May 28
Lead ML evaluation for prediction models powering the Waymo Driver.
$251k–$310k
EvaluationsWaymo · Mountain View, CA, USA; San Francisco, CA, USA +2 · Onsite · Dec 2025
Build evaluation frameworks that establish ultimate truth for Waymo Driver safety.
$175k–$215k
EvaluationsWaymo · London, UK +1 · Onsite · Jul 14
Build ultra-realistic AV simulations using foundation models.
GBP 155k–GBP 163k
EvaluationsWaymo · Mountain View, CA, USA; San Francisco, CA, USA +1 · Onsite · Jun 13
Prove mathematically that Waymo's virtual world is truly real.
$213k–$263k
EvaluationsWaymo · Mountain View, CA, USA +1 · Onsite · Dec 2025
Lead architecture for single source of truth powering Waymo's ride-hail expansion.
$281k–$356k
EvaluationsWaymo · Hyderabad, Telangana, India +1 · Onsite · Jan 8
Ensure safety and reliability of the Waymo Driver autonomous service.
INR 2900k–INR 3510k
EvaluationsWaymo · Mountain View, CA, USA; San Francisco, CA, USA; New York, NY, USA +2 · Onsite · May 27
Build signals measuring performance and driving quality of the Waymo Driver.
$251k–$310k
EvaluationsWaymo · Mountain View, California, USA +1 · Onsite · Sep 16
Develop core simulator functionality for safety evaluation of internal models.
$146k–$177k
EvaluationsWaymo · Mountain View,CA, USA; San Francisco, CA, USA; New York, NY, USA +1 · Onsite · Mar 25
Design core APIs powering safety and quality evals for autonomous driving scale.
$213k–$263k
EvaluationsWaymo · Mountain View, CA, United States +1 · Onsite · Dec 2025
Build next-gen ML evaluation metrics for the Waymo Driver.
$281k–$356k
EvaluationsWaymo · Mountain View, California, United States; San Francisco, California, United States. +1 · Onsite · Sep 17
Prove a virtual world is real by grading Waymo's autonomous driving simulator.
$251k–$310k
EvaluationsWaymo · Mountain View, CA, USA +1 · Onsite · Oct 6
Optimize eval pipelines powering the Waymo Driver's autonomous decisions.
$125k
EvaluationsWaymo · Mountain View, CA, USA +1 · Onsite · Oct 5
Build data platforms supporting ML launch evals for the Waymo Driver.
$146k–$177k
EvaluationsWaymo · Mountain View, CA, USA; San Francisco, CA, USA +2 · Onsite · Jun 9
Build data platforms powering evaluation of the Waymo Driver software.
$213k–$263k
EvaluationsWaymo · Mountain View, California, United States +1 · Onsite · Aug 2025
Build distributed evaluation platforms scaling across compute, data and environments.
$238k–$302k
EvaluationsWaymo · Warsaw, Poland +1 · Onsite · Sep 18
Prototype scheduling algorithms to smooth computational load in simulation.
Salary not listed
EvaluationsCartesia · *HQ - San Francisco, CA · Onsite · Oct 2025
Design eval frameworks capturing how models reason, remember, and interact.
$220k–$350k
EvaluationsCursor · San Francisco +1 · Onsite · Jun 3
Lead the team creating high-signal eval datasets for coding agents.
Salary not listed
EvaluationsCursor · San Francisco +1 · Onsite · Apr 13
Build measurement and eval infrastructure to make the core agent better over time.
Salary not listed
Evaluations