AI Research Engineer (Agentic Reinforcement Learning)
Jobgether🇦🇪United Arab EmiratesFull TimeEngineering
Fully remote
“Fully Remote Work: Work remotely from anywhere in the world, with a globally distributed team” — from the job posting
- Employee
Listed on 2 job boards, which is a stronger signal than one board alone.
Job Description
📋 Description
- Research and develop reinforcement learning algorithms for multimodal models, including
- Design and implement scalable reinforcement learning infrastructure supporting distributed training
- Develop and optimize reward modeling strategies to improve training stability, align model behavior
- Create, curate, and maintain multimodal simulation environments and training datasets…
computer visiondeep learningmultimodal aireinforcement learningpytorchdiffusion modelsdistributed training
Match
Sign in and add your skills to see how well you match this role.
Tailor your CV to this jobPro
Pro rewrites your CV bullets for this job and checks every line against your CV, dropping anything it can't back up.
See ProAlso available on
Back to all jobs