About the role
The research team develops new methods for evaluating and improving advanced AI systems. The scientist identifies research gaps, designs experiments, and creates benchmarks and datasets to advance AI capabilities in areas like reliability and agentic science.
Our summary of the posting; the original is on the Turing careers page.
What the posting requires
- Required
- Research
- Experimental design
- Python
- Benchmark
- Benchmarks
- Evaluations
- Task-generation
- Synthetic data
- Task selection
- Training signal
- Preferred
- Publication record
These tags are our reading of the posting. They can miss something; the original posting is the reference.