GenAI Prompt Engineering | Hybrid | (GC)/(USC)
GenAI Prompt Engineering We are seeking a AI prompt engineer to join an innovative and high-impact team building AI capabilities within enterprise systems for a leading wealth management client. In this role, you will help design and optimize prompt-driven experiences that make AI assistants, automation workflows, and decision-support tools more effective, reliable, and scalable across the business. This is an opportunity to shape the next generation of enterprise AI in a highly visible environment, where innovation, rigor, and business value all matter. You’ll contribute to prompt design, testing, evaluation, optimization and governance while helping establish repeatable patterns for responsible AI use in a regulated financial services setting. The ideal candidate is curious, hands-on, and energized by solving real-world problems at the intersection of AI, enterprise technology, and wealth management This role partners with product, engineering, UX, data, and domain teams to translate user needs into effective instructions, guardrails, and interaction patterns that drive high-quality model outputs. The position requires strong judgment, experimentation discipline, and a practical understanding of LLM behavior, context management, and evaluation.
Key Responsibilities
Design and refine prompts, prompt chains, and prompt templates for enterprise AI use cases Develop instructions, examples, guardrails, and system messages to improve response quality and consistency Test model behavior across scenarios, edge cases, and failure modes Create and apply evaluation criteria for relevance, accuracy, tone, safety, and task completion Collaborate with product and engineering teams to embed prompts into production workflows Analyze user feedback, logs, and output quality to identify prompt improvements Support retrieval-augmented generation workflows by optimizing context selection and prompt grounding Establish prompt versioning, testing, documentation, and governance practices Work with domain experts to encode business logic, policy requirements, and domain terminology
Required Qualifications
Bachelor’s degree in Computer Science, Engineering, Linguistics, Cognitive Science, Information Systems, or related field 6+ years of experience in AI, NLP, conversational design, product writing, software engineering, or related discipline Hands-on experience designing and testing prompts for LLM-based applications Strong understanding of prompt patterns, context windows, hallucination risks, and model limitations Experience with AI evaluation methods, experimentation, and quality measurement Ability to communicate technical trade-offs to both technical and non-technical stakeholders
Preferred Qualifications
Experience with RAG, vector databases, semantic search, or AI orchestration frameworks Familiarity with Python, SQL, APIs, or workflow automation Experience in large enterprise environments, consulting / professional services, regulated, or high-compliance environments Knowledge of prompt testing tools, observability, or LLMOps practices Background in UX writing, conversation design, or content strategy Core Competencies Precision in language and instruction design Analytical thinking and experimentation Cross-functional collaboration Strong attention to quality and consistency Comfort with ambiguity and rapidly changing AI capabilities Practical problem solving with a bias toward measurable outcomes