Research Engineer / Research Scientist, RL Frontiers

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

About the company

the company’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the role

Reinforcement learning is how Claude learns to reason, write code, and act autonomously over long horizons. The RL Scaling team works on how RL scales: what happens to throughput, stability, and learning efficiency as models get larger, episodes get longer, and compute grows by orders of magnitude, and what has to change in our algorithms and systems to keep getting returns from that scale.

This role sits squarely across research and engineering. You'll develop next-generation architectures and RL algorithms, take them from a small-scale result to a frontier-scale run, and understand every place they behave differently along the way. You'll build the systems that set how fast the team can iterate: how many experiments, at what scale, and how quickly we can trust the results. And you'll work on the company's largest and fastest RL runs, where the gap between a good idea and a working one is often a problem no one has solved yet.

Key responsibilities

• Study how RL training and sampling scale with model size, context length, and compute, and find the algorithmic and systems changes that keep scaling efficient
• Develop next-generation model architectures and RL algorithms, and make them run efficiently at frontier scale
• Take promising small-scale results to frontier-scale runs, and diagnose why they behave differently when they get there, whether the cause is numerical, algorithmic, or systemic
• Build the experimental infrastructure that sets research velocity: fast, reproducible comparisons of architecture and algorithm variants at meaningful scale
• Own end-to-end performance of our largest RL runs, from research code down to the hardware
• Build performance and cost models for proposed architecture and algorithm changes, and use them to decide which ideas get scaled
• Investigate training dynamics at scale, including instabilities, divergence, and throughput regressions, and trace them to root cause

Minimum qualifications

• Deep familiarity with modern transformer language models, including their architecture, training dynamics, and the behavior of large-scale optimization
• Hands-on experience training large models in a distributed setting, including the tradeoffs between data, tensor, and pipeline parallelism
• A track record of original technical work in ML training or systems, such as new methods, architectures, or optimizations, demonstrated through research, open-source, or production impact
• Ability to design rigorous experiments at scale, including baselines, ablations, and enough statistical care to trust a result that costs real compute
• Ability to reason quantitatively about the compute, memory, and communication costs of a model or algorithm
• Strong programming skills in Python and JAX or PyTorch, and comfort reading and changing code at every layer of the stack

Preferred qualifications

• Research experience in reinforcement learning, optimization, or large-scale training, published or otherwise
• Experience developing RL algorithms for language models
• Experience with scaling laws or other quantitative models of training efficiency
• Experience designing or modifying transformer architectures beyond standard configurations
• Experience scaling training to large fleets of accelerators and debugging the problems that only appear at scale
• Deep understanding of numerics in large-scale training, including low-precision formats and sources of instability
• Familiarity with how GPU or TPU performance characteristics shape architecture and algorithm choices
• Experience with C++ or Rust

Representative projects

• Characterize how a new RL algorithm's throughput and learning efficiency change from small models to frontier scale, and fix what breaks
• Develop a new attention variant, get it working at full scale, and measure how its quality and throughput compare to the baseline
• Prepare our next largest-ever RL run: find what breaks when model size, context length, and compute all grow at once, and fix it before launch
• Trace a loss instability that only appears past a certain scale to its root cause, and work out whether the fix belongs in the algorithm, the numerics, or the system
• Build a model that predicts the throughput and cost of a proposed architecture change before anyone writes the kernel

The annual compensation range for this role is listed below.

For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.

Annual Salary:

$500,000—$850,000 USD

LogisticsMinimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience

Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position

Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.