דרושים Senior AI Agent Evaluation Analyst בכל הארץ

About the Role

We are hiring a Senior AI Agent Evaluation Analyst to help benchmark and enhance the reasoning, reliability, and policy adherence of advanced AI agents.

You’ll evaluate multi-step reasoning trajectories, analyze structured agent data, and ensure models behave consistently and ethically across realistic scenarios.

Key Responsibilities

• Evaluate AI agents’ reasoning paths, tool-use accuracy, and decision logic in complex tasks.
• Identify inconsistencies, hallucinations, or policy violations within multi-step reasoning.
• Analyze structured data (JSON/YAML) to verify agent actions and tool calls.
• Benchmark large language models (GPT, Claude, Gemini, etc.) for reasoning accuracy and behavioral consistency.
• Document findings, improve evaluation frameworks, and contribute to quality standards.
• Collaborate with Research, Policy, and AI Safety teams to refine evaluation methodologies.

Required Qualifications

• 7+ years of professional experience in AI Agent Evaluation, LLM Assessment, AI Safety, or Red Teaming.
• Proven expertise in multi-step reasoning evaluation, policy logic, and trajectory analysis.
• Familiarity with LangChain, RAG, Prompt Engineering, and structured data formats (JSON/YAML).
• Strong analytical writing, logical reasoning, and documentation skills in English.
• Hands-on experience with LLMs such as GPT, Claude, or Gemini.
• Excellent attention to detail and ability to evaluate abstract, ambiguous reasoning tasks.

Preferred Skills

• Understanding of RLHF (Reinforcement Learning from Human Feedback) and model alignment.
• Knowledge of AI Policy, Safety Evaluation, and Red Teaming frameworks.
• Experience developing evaluation rubrics or QA frameworks for AI systems.
• Exposure to projects with OpenAI, Anthropic, Google, Appen, TELUS, or Scale AI.

Benefits

• 100% remote role with flexible hours.
• Competitive compensation with performance-based incentives.
• Opportunity to shape next-generation agentic AI systems and reasoning benchmarks.
• Work with global experts at the intersection of AI evaluation and safety research.

E: | לפנייה למשרה יש להגיש מועמדות |

📩 Think you’ve got the brain for it?

Apply here 👉 AI Agent Evaluation Analyst Application Form