Role: AI Engineer – Agent Evaluation Specialist

Location: Los Angeles, CA (Hybrid)

Duration: 3+ Months (Possible Extension)

Primary Focus: Hands-on Agent Evaluation

Specialisation: Agentic AI, AWS Bedrock AgentCore, Claude Agent SDK, Langfuse, AI Observability & Evaluation

We are looking for an AI Engineer with strong, practical experience in evaluating LLM-powered agents, rather than someone focused primarily on building or developing agents.

Key Requirements (Must-Have):

• LLM-as-a-Judge: Hands-on experience designing, implementing, and running LLM-based evaluation frameworks to assess agent response quality, accuracy, relevance, and reliability.
• Golden Dataset Development: Experience collaborating with Business Analysts and stakeholders to create, validate, and maintain golden datasets that serve as benchmarks for agent evaluation.
• Langfuse: Practical experience instrumenting AI agents using Langfuse, including tracing agent execution, capturing evaluation scores, monitoring performance, and troubleshooting failures.
• Agent Evaluation: Strong understanding of end-to-end agent evaluation, including testing agent behavior, tool usage, reasoning workflows, and response quality.

Critical Screening Criteria:

Candidates must demonstrate actual implementation experience with agent evaluation frameworks, not just theoretical knowledge or general GenAI/LLM development.

Agent evaluation is the core requirement and will be the primary selection criterion.

All your information will be kept confidential according to EEO guidelines.