AI Research Scientist – Frontier STEM Benchmarks

turing; New York (NY); Remote; USD 150,000 - 300,000; Full time

Benefits offered by this job

Equity in compensation

Job summary

Turing is advancing frontier AI research by creating rigorous benchmarks, synthetic data, and robust evaluation methods for transformative AI systems. You will identify gaps, propose new research directions, and execute projects from hypothesis to publication, collaborating with leading labs and enterprises.

The role emphasizes research independence, publication potential, and building scalable evaluation pipelines that impact real-world AI deployment across STEM and industry domains.

Qualifications

• PhD or equivalent research experience in ML/CS or highly technical field.
• Strong ability to formulate and execute original research.
• Excellent experimental design, quantitative reasoning, and scientific judgment.

Responsibilities

• Identify high-impact gaps in benchmark and evaluation literature and design new benchmarks.
• Develop evaluations for emerging model capabilities and create reliable methodologies.
• Study hallucination, uncertainty, calibration, and verification in frontier AI.
• Design workflows for literature search, coding, simulation, and multi-step reasoning in research projects.

Skills

Python programming

Experimental design

Quantitative reasoning

Scientific writing

LLMs knowledge

Rapid prototyping

Communication skills

Education

PhD or equivalent

Tools

Job description

Turing is advancing frontier AI research by creating rigorous benchmarks, synthetic data, and robust evaluation methods for transformative AI systems. You will identify gaps, propose new research directions, and execute projects from hypothesis to publication, collaborating with leading labs and enterprises.

The role emphasizes research independence, publication potential, and building scalable evaluation pipelines that impact real-world AI deployment across STEM and industry domains.