Prompt Engineer
About the job Prompt Engineer Role & Responsibilities Overview:Prompt Design & OptimizationDesign prompts for - summarization, risk insights, adverse media analysis, underwriter assistant agent etc.duplicate explanation, decision supportOptimize prompts for accuracy, grounding, and consistencyEvaluation & Continuous ImprovementDefine evaluation scenarios and validation datasetsUse LLM-as-judge and feedback loops to improve responsesContinuously refine prompts based on - model performance, user feedbackRAG & Assistant EnablementWork with AI engineers to - improve retrieval quality, design context injection strategiesEnsure outputs are - grounded, explainable, aligned with underwriting logicBusiness AlignmentTranslate underwriting workflows into prompt logicIncorporate domain-specific language, risk indicators, and business rulesCollaborate with underwriters and SMEsPrompt GovernanceMaintain prompt library and versioningDefine templates for different LOBs and use casesEnsure consistency across assistant and workflowsCandidate Profile:Experience: 5-8+ years with 2-4+ years in GenAI / prompt engineeringDomain (Mandatory): Strong insurance / underwriting knowledgeEducation: Bachelor's/Master's in Engineering, Data Science, Business Analytics, or relatedProfile Type: Hybrid business + technical, strong analytical thinkerTechnical skills:GenAI & Prompting - prompt engineering techniques (few-shot, chain-of-thought, structured prompts);Experience with Azure OpenAI / LLM APIs; Prompt versioning and optimizationRAG & Retrieval Awareness - understanding of Azure AI Search and retrieval behavior; Context design and grounding strategies; Ability to reduce hallucinations via prompt + retrieval designEvaluation & Quality - LLM-as-judge / evaluation frameworks; Output validation and benchmarking; A/B testing of promptsSafety & Governance - Awareness of guardrails (NeMo Guardrails); PII handling (Presidio); Responsible AI practicesCollaboration & Tools - Familiarity with APIs, JSON, and structured outputs; Basic Python; Working with AI engineers and data teams