Applied Research Scientist: Safety & Alignment RL
Listed on 2026-10-12
-
Research/Development
Research Scientist, AI Business & Operations
Fleet is seeking an Applied Research Scientist to advance robust reward design, telemetry, and production systems for aligned reinforcement learning agents. You will analyze model trajectories, help co-design RL environments, and collaborate with frontier labs to improve safety across tasks.
You will work on designing comprehensive telemetry, building verifiers, and implementing oversight systems to detect misaligned behaviors, while collaborating with safety researchers to push the boundaries
This posting is for the Applied Research Scientist:
Safety & Alignment for RL role at Fleet AI, Inc., based in San Francisco, CA, United States.
We are looking to fill the Applied Research Scientist:
Safety & Alignment for RL position at Fleet AI, Inc. in San Francisco, CA, United States.
The Applied Research Scientist:
Safety & Alignment for RL role at Fleet AI, Inc. is now open for applications in San Francisco, CA, United States.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).