Frontier RL Research Engineer: Scale & Systems

United States Digital Space LLC; San Francisco (CA); Hybrid; USD 500,000 - 850,000; Full time

Job summary

United States Digital Space LLC is seeking a senior RL researcher to scale reinforcement learning systems from small results to frontier-scale runs. You will design and implement next-generation architectures and RL algorithms, diagnose scale-related behavior, and own end-to-end performance from research code to hardware.

The role emphasizes building fast, reproducible experimentation infrastructure, evaluating throughput and cost implications, and collaborating across research and engineering

Qualifications

• Experience with modern transformer language models, training dynamics, and large-scale optimization.
• Hands-on experience training large models in a distributed setting with data, tensor, and pipeline parallelism.
• Track record of original ML research or production impact (methods, architectures, optimizations).
• Ability to design rigorous, scalable experiments with baselines, ablations, and robust statistics.

Responsibilities

• Study how RL training and sampling scale with model size, context length, and compute; identify changes to keep scaling efficient.
• Develop next-generation model architectures and RL algorithms for frontier-scale runs.
• Take small-scale results to frontier-scale, diagnosing behavior and root causes (numerical, algorithmic, or systemic).
• Build experimental infrastructure for fast, reproducible comparisons at meaningful scale.
• Own end-to-end performance of the largest RL runs from research code to hardware.
• Build models to estimate throughput and cost of architecture changes.

Skills

Transformer models

Distributed training

Python

JAX or PyTorch

C++ or Rust

Experiment design

Cost & scaling

Education

Bachelor's degree or equivalent

Job description

United States Digital Space LLC is seeking a senior RL researcher to scale reinforcement learning systems from small results to frontier-scale runs. You will design and implement next-generation architectures and RL algorithms, diagnose scale-related behavior, and own end-to-end performance from research code to hardware.

The role emphasizes building fast, reproducible experimentation infrastructure, evaluating throughput and cost implications, and collaborating across research and engineering