Preference Model · San Francisco · Onsite · Nov 11
Build scalable infrastructure powering post-training on in-house RL environments.
$200k–$350k
Post-Training ResearchPM
Preference Model
HiringInfrastructureSuperintelligence data research company building RL environments for capable, better-aligned AI.
www.preferencemodel.com/ ↗CHECKED 16H AGO
Open roles (6)
6 open roles
Preference Model · San Francisco · Onsite · Nov 11
Train and evaluate models on proprietary RL environments to validate quality.
$200k–$350k
Post-Training ResearchPreference Model · San Francisco · Onsite · Nov 11
Build RL environments that train capable, better-aligned superintelligences.
$200k–$350k
Post-Training ResearchPreference Model · San Francisco · Onsite · Nov 10
Own systems taking RL environments from builder repo to lab training runs.
$180k–$350k
Platform EngineeringPreference Model · San Francisco · Onsite · Nov 10
Own frontier lab relationships end-to-end from sales to delivery and expansion.
$180k–$240k
Strategy and OperationsPreference Model · San Francisco · Onsite · May 4
Design RL environments that teach frontier models ML research tasks.
$165k–$200k
Software EngineeringLab profile
About the lab
What they build
- RL environments for superintelligence training
Known for
- Reinforcement learning environments
- Reward signals for capability and alignment