Prompt Engineer

Inizio Partners Corp•New York, NY

19h•Hybrid

About The Position

We are seeking a skilled Prompt Engineer to join our team. In this role, you will be responsible for designing, optimizing, and governing prompts for various AI applications, including summarization, risk insights, adverse media analysis, and an underwriter assistant agent. You will also focus on improving retrieval quality, designing context injection strategies, and ensuring that AI outputs are grounded, explainable, and aligned with underwriting logic. This role requires a hybrid business and technical profile with strong analytical thinking skills and a deep understanding of insurance and underwriting workflows.

Requirements

5-8+ years of experience
2-4+ years in GenAI / prompt engineering
Strong insurance / underwriting knowledge (Mandatory)
Bachelor's/Master's in Engineering, Data Science, Business Analytics, or related field
Hybrid business + technical profile
Strong analytical thinker
Prompt engineering techniques (few-shot, chain-of-thought, structured prompts)
Experience with Azure OpenAI / LLM APIs
Prompt versioning and optimization
Understanding of Azure AI Search and retrieval behavior
Context design and grounding strategies
Ability to reduce hallucinations via prompt + retrieval design
LLM-as-judge / evaluation frameworks
Output validation and benchmarking
A/B testing of prompts
Awareness of guardrails (NeMo Guardrails)
Awareness of PII handling (Presidio)
Awareness of Responsible AI practices
Familiarity with APIs, JSON, and structured outputs
Basic Python
Experience working with AI engineers and data teams

Responsibilities

Design prompts for summarization, risk insights, adverse media analysis, underwriter assistant agent, duplicate explanation, and decision support.
Optimize prompts for accuracy, grounding, and consistency.
Define evaluation scenarios and validation datasets.
Utilize LLM-as-judge and feedback loops to improve responses.
Continuously refine prompts based on model performance and user feedback.
Work with AI engineers to improve retrieval quality and design context injection strategies.
Ensure AI outputs are grounded, explainable, and aligned with underwriting logic.
Translate underwriting workflows into prompt logic.
Incorporate domain-specific language, risk indicators, and business rules.
Collaborate with underwriters and SMEs.
Maintain prompt library and versioning.
Define templates for different LOBs and use cases.
Ensure consistency across assistant and workflows.