Research Engineer – Experimental ML Systems (Sunnyvale)

Research Engineer – Experimental ML SystemsSan Francisco, CA | OnsiteEarly-stage AI research lab | Revenue-generatingAn AI research lab focused on alignment, interpretability, and reinforcement learning is hiring engineers to build experimental systems that study how models generalize, fail, and become misalignedThis is not a traditional ML infrastructure role focused on scaling training runsThe work is highly exploratory: designing synthetic environments, building research tooling from scratch, and running experiments to better understand model behaviorYou'll work on:Designing synthetic RL environments for studying model behavior under distribution shiftBuilding experimental platforms for generalization, robustness, and alignment researchStudying reward hacking, deceptive behavior, and goal misgeneralizationPrototyping novel training setups and evaluation harnessesDeveloping benchmarks that measure internal consistency - not just outputsRapidly testing research hypotheses through code and experimentsExample areas include:Toy worlds where models develop deceptive or power-seeking strategiesExperimental systems for activation-level interventionsRobustness benchmarks focused on internal reasoning patternsStrong fits often come from:Experimental ML or RL researchSecurity research, adversarial thinking, or red-teamingBuilding small research prototypes vs production systemsStrong engineering ability combined with curiosity and creativityPhD preferred, but the key requirement is the ability to build novel research systems from scratchThis is not:Scaling frontier model trainingProduction ML infrastructureData engineering or product MLThis role is for people who want to invent new experimental systems - not optimize existing pipelinesInterested? Hit apply & Drop me a message!