Research Engineer, Multimodal Reinforcement Learning
Is this job for you?
Build my CV Build your CV and see how well you match this role — and every other one.
The role
Design and implement scalable multimodal reinforcement learning algorithms for multi-turn reasoning in text + vision environments.
Scale training environments using an ecosystem of autoraters and autousers to enable semi-verifiable learning at scale.
Advance retrieval-augmented reasoning to bridge single-turn and multi-turn embeddings and improve grounding in visuals.
Plan, run, and analyze complex RL experiments with rigorous scientific methodology and reproducibility.
Collaborate across teams to align research with product needs in Search, Lens, and YouTube and drive shared pipelines.
Contribute to cutting-edge models, publish results, and influence next-generation AI capabilities while upholding safety and ethics.
Scale training environments using an ecosystem of autoraters and autousers to enable semi-verifiable learning at scale.
Advance retrieval-augmented reasoning to bridge single-turn and multi-turn embeddings and improve grounding in visuals.
Plan, run, and analyze complex RL experiments with rigorous scientific methodology and reproducibility.
Collaborate across teams to align research with product needs in Search, Lens, and YouTube and drive shared pipelines.
Contribute to cutting-edge models, publish results, and influence next-generation AI capabilities while upholding safety and ethics.
See the full job post
Responsibilities, requirements, skills and benefits — create your free account.
Already have an account? Log in
Similar openings
Other roles that could suit you.