Research Scientist - Post Training

Reinforced Learning; Town of Tonawanda (NY); On-site; USD 90,000 - 130,000; Full time

Job summary

Reinforced Learning in the United States seeks a researcher to design and run training experiments that isolate how datasets affect model behavior, including supervised fine-tuning (SFT) and RL-based post-training, measuring improvements under varied conditions.

You will collaborate with partner labs, publish external-facing research, and iterate on data quality based on results to demonstrate clear evidence of data-driven improvements.

Qualifications

• Strong familiarity with LLM training and evaluation methodologies.
• Ability to design lightweight experiments, move fast, and extract actionable insights from messy results.
• Comfort working across domains (finance, software engineering, policy, and more).
• Bias toward building over theorizing.

Responsibilities

• Run controlled SFT and RL experiments to measure the impact of datasets on model performance.
• Help build public evals and new data types that push the frontier.
• Publish external-facing research, blog posts, and technical reports.
• Work with internal SPLs to iterate on data quality based on results.

Skills

LLM training

Experiment design

Cross-domain experience

Data quality focus

Education

Bachelor’s degree (or equivalent)

Master’s by research

Job description

Overview

Your job is to prove that our data works. You will design and run training experiments that isolate the impact of our datasets on model behavior. This includes SFT and RL-based post-training, where you’ll measure how different data sources shift capability, generalization, and alignment. Working closely with partner labs, you will turn our datasets into clear, defensible evidence: this data → this improvement → under these conditions. This is experimental, high-leverage work.

Responsibilities

• Run controlled SFT and RL experiments to measure the impact of our datasets on model performance.
• Help build public evals and new data types that push the frontier.
• Publish external-facing research, blog posts, and technical reports.
• Work with internal SPLs to iterate on data quality based on your results.

Required Qualifications

• Strong familiarity with LLM training and evaluation methodologies.
• Ability to design lightweight experiments, move fast, and extract actionable insights from messy results.
• Comfort working across domains (you'll touch finance, software engineering, policy, and more).
• A bias toward building over theorizing.

Preferred Qualifications

• Great candidates are undergrad research or master's research (but haven't done a phd).
• Genuine obsession with how data structure, selection, and quality drive model behavior.