Research Scientist - Frontier Data - LLM training pipelines, RLHF or RLVR

 

Design data slices and explore data shapes that expose meaningful model failure modes across domains, including finance, code, and enterprise workflows

 

Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines

 

Model annotator behavior and run experiments to improve different model capabilities

 

Develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on model alignment and capability

 

Partner with lab research teams to translate their training objectives into concrete data and evaluation specifications

 

Move fast from hypothesis to experiment, extract actionable insights from messy results, and iterate quickly

 

 

Strong quantitative instincts with familiarity with LLM training pipelines, RLHF or RLVR, or evaluation methodology. Does not need a PhD but must have the research depth of a strong undergrad or master's researcher

 

Genuine obsession with how data structure, selection, and quality drive model behavior. This is the core of the work and must be intrinsically motivated

 

Ability to design lightweight experiments, move fast, and extract actionable insights from messy and incomplete results

 

Comfort working across domains, the work touches finance, software engineering, policy, and more. Must be able to context-switch and reason clearly across all of them

 

Bias toward building over theorizing. Ships experiments and iterates, does not get stuck in design

 

 

Prior work or internship at RL environment companies, AI safety organizations, or benchmarking organizations such as METR or Artificial Analysis

 

Background in evaluation methodology, benchmark design, or dataset curation at a lab or research organization

 

Exposure to annotator modeling, reward signal design, or alignment-related research

The standard base is 150 to 250k, but they also engage in profit sharing, so their total cash comp will land between 250 and 450k, and then, of course, there's equity on top of that.