Anthropic in London, UK, is seeking a Research Engineer for RL Scaling Science to design and run large-scale RL experiments and translate verified results into production training recipes. The role bridges research and production, requiring collaboration across teams and robust data interpretation.
You will study how RL performance scales with compute, model size, and horizons, and help develop benchmarks for long-horizon RL.
#J-18808-LjbffrRL Scaling Research Engineer (Hybrid) — Lab to Production employer: Anthropic
Anthropic is an exceptional employer for those passionate about advancing reinforcement learning in a collaborative and innovative environment. With competitive compensation, generous vacation and parental leave, and flexible working hours, employees enjoy a supportive work culture that prioritises both personal and professional growth. Located in a vibrant office space, team members have the unique opportunity to engage directly with cutting-edge research while making meaningful contributions to the responsible scaling of AI.
