Elicit

Engineer

• Understand decisions users and domain experts need to make in scientific R&D and commercial strategy
• Identify objectives, constraints, available evidence, and important unknowns
• Define and measure good reasoning using example inspection, expert judgment, and quantitative analysis
• Build evaluations for underspecified problems and validate that scores reflect meaningful improvements
• Investigate model and agent failures and turn observations into testable hypotheses
• Experiment with problem decomposition, context, tools, information-seeking, and self-checking approaches
• Design agent environments and representations for problems, evidence, assumptions, and unresolved questions
• Design reliable software abstractions, data structures, and component boundaries for reasoning workflows and evaluations
• Balance simplicity, flexibility, reliability, latency, and cost
• Write maintainable code and participate in design and code reviews
• Test, monitor, diagnose, and integrate systems into the product
• Collaborate with engineers, product, design, and domain experts
• Take problems from investigation and experimental design through implementation and product use
• Improve systems built around existing frontier models, with training or finetuning where useful

Explore Model Behavior Engineer – Reasoning and Decision Making at Elicit. Review requirements and application details.