Skills & Keywords
Agent workflowsArize PhoenixComplianceCost OptimizationEmbeddingsEvaluationHallucination detectionHuman-in-the-loopLLM-as-a-JudgeLangchainLanggraphLangsmith
Job Description
Build AI application layer prompt orchestration tool calling retrieval RAG embeddings agent workflows structured outputs; Build safety and reliability guardrails ensure quality compliance operational requirements; Design build and ship production LLM powered features end to end; Design observability systems accuracy latency cost hallucination rates model behavior; Develop evaluation infrastructure regression suites LLM as a judge synthetic datasets human review workflows quality metrics; Evaluat
View full posting