maneki.
POST
MANEKI/JOBS/NOUS RESEARCH
Nous Research
Nous Research
4 open roles on Maneki

Full TimeMLE (Reinforcement Learning Training Infrastructure)

Mid / Senioron site
LOCATION
POSTED
8mo ago
APPLY DIRECTLY
Application goes to Nous Research's own career page
APPLY ON NOUSRESEARCH
Maneki aggregates jobs from top Web3 companies. We redirect you to the original posting — no middleman, no added steps.

Required skills

Machine LearningReinforcement LearningDistributed ComputingMicroservicesPerformance Engineering

Job description


We’re looking for an MLE to build and scale distributed reinforcement learning systems for model training. You’ll deploy elastic environment microservices, design reward systems and optimize multi-node and multi-datacenter training pipelines.

Responsibilities:

  • Designing and implementing RL pipelines from reward modeling to policy optimization
  • Optimizing RL training stability and sample efficiency for large models
  • Verifying numerical correctness across inference and training
  • Performance engineering on trainer-inference communication
  • Validating methods from recent publications

Qualifications:

  • Hands-on experience with reinforcement learning in production systems
  • Deep understanding of policy-space methods (GRPO, PPO, etc.)
  • Experience profiling distributed systems

Preferred:

  • History of OSS contributions
  • Knowledge of TorchTitan and SGLang or vLLM