Research Scientist – Frontier Evaluations

Reinforced Learning; Town of Tonawanda (NY); On-site; USD 140,000 - 210,000; Full time

Job summary

Reinforced Learning seeks Research Scientists to design and publish rigorous evaluations for frontier AI systems. You will lead end-to-end evaluation development across agentic, coding, and safety domains and work with experts in healthcare, STEM, and finance to close important capability gaps with public research.

You will own evaluation development, publish benchmark results, and contribute to reproducible research practices across disciplines.

Qualifications

• Proven ability to publish benchmarks or research papers.
• Strong scientific writing and communication.
• Commitment to experimental rigor with baselines and ablations.

Responsibilities

• Lead end-to-end design, validation and launch of frontier AI benchmarks.
• Collaborate with researchers to develop evaluations around model failures and domain gaps.
• Analyze capabilities and failure modes using rigorous experimental methods.
• Build reproducible evaluation systems and infrastructure.
• Communicate results via reports and research papers.

Skills

Research publications

Technical writing

Experimental design

Reproducible research practices

Education

PhD in a related field

Job description

Overview

Reinforced Learning is hiring Research Scientists to design and publish rigorous evaluations for frontier AI systems. The role spans agentic, coding, and safety evaluations, as well as expert-domain evaluations involving applied AI in healthcare, STEM, finance, and related fields. You will own evaluation development end to end and collaborate across disciplines to turn important capability gaps into rigorous public research.

Responsibilities

• Lead the end-to-end design, validation, launch, and continuous improvement of frontier AI benchmarks.
• Partner with researchers and domain experts to develop evaluations around meaningful model failures, gaps in existing coverage, and high-priority domains.
• Analyze model capabilities and failure modes using rigorous experimental design and statistical methods.
• Build reproducible evaluation systems, including harnesses, graders, and benchmark infrastructure.
• Collaborate with researchers to post-train models and measure the resulting performance gains.
• Communicate results through benchmark reports, technical articles, and research papers.

Required Qualifications

• Strong record of publishing benchmarks or research papers.
• Clear technical communication and strong scientific writing skills.
• Commitment to experimental rigor, including baselines, ablations, statistical validity, and contamination controls.
• Ability to take an ambiguous evaluation question from initial scoping through a reproducible public release.
• Depth in agentic, coding, and safety evaluations or applied machine learning in an expert domain.

Preferred Qualifications

• PhD in a related technical field.
• Research publications at leading conferences or peer-reviewed journals.
• Interest in multidisciplinary research and the creativity to combine methods and insights from AI, engineering, science, and other expert domains.