Prompt Engineer

Title: Prompt Engineer Location: Jersey City, NJ (4 Days Onsite) Role purpose Design, test, govern, and continuously improve prompts, system instructions, conversation flows, and interaction patterns for AIRP LLM applications and related citizen-development experiences. The role ensures model outputs are accurate, grounded, safe, consistent, cost-aware, and aligned with business and compliance expectations. Client · Prompt work must support enterprise business use cases, not generic chatbot experimentation. · Reusable prompt patterns should be suitable for AIRP and, where applicable, Copilot Studio / Power Platform citizen-development scenarios. · Candidates must understand prompt security, sensitive data handling, citations/grounding, and structured evaluation. Primary ownership · Prompt patterns, system instructions, response templates, and conversation policies for AIRP LLM use cases. · Prompt testing, versioning, evaluation, and quality-improvement workflows. · Reusable prompt libraries and guardrail patterns for business teams and responsible citizen development where applicable. Key responsibilities · Design prompts for chatbots, copilots, RAG systems, document analysis, summarization, workflow agents, knowledge assistants, and decision-support experiences. · Develop system prompts, few-shot examples, tool-use instructions, response formats, escalation logic, citation behavior, and conversation policies. · Optimize prompts for KYC support, credit underwriting support, governance tracking, pitch book generation, Banker 360, Customer 360, deal library intelligence, financial crime quality, and sanctions screening use cases. · Build reusable prompt libraries and templates aligned to enterprise standards, business domains, AIRP patterns, and citizen-development guardrails. · Evaluate prompt performance using metrics such as task success, groundedness, hallucination rate, completeness, safety, user satisfaction, latency, and token cost. · Partner with engineers to implement prompt versioning, testing, deployment, and monitoring in production systems and CI/CD workflows. · Support RAG quality by assessing retrieval context, chunking quality, source citation behavior, response synthesis, and missing-context behavior. · Conduct adversarial testing for prompt injection, jailbreaks, instruction conflicts, sensitive-data leakage, unsafe outputs, and unauthorized tool use. Must-have candidate profile · Strong understanding of LLM behavior, prompt design, tokenization, context windows, RAG, embeddings, and model limitations. · Hands-on experience with OpenAI APIs, Azure OpenAI, AWS Bedrock, Anthropic, LangChain, LlamaIndex, Semantic Kernel, Copilot Studio, or similar platforms. · Ability to debug LLM outputs using structured testing, error analysis, and iterative refinement. · Strong writing, analytical, communication, and stakeholder-management skills. · Understanding of prompt-security risks including prompt injection, jailbreaks, data leakage, hallucination, and instruction conflicts. · Ability to create repeatable prompt templates and evaluation evidence suitable for enterprise governance. Preferred experience · Background in NLP, conversational AI, UX writing, technical writing, product design, knowledge management, business analysis, or financial-services operations. · Experience in financial services, legal, compliance, risk, operations, customer support, banker productivity, or enterprise knowledge domains. · Familiarity with Microsoft Copilot Studio, Power Platform, prompt registries, A/B testing, human review workflows, and evaluation tooling.