Prompt Engineer

Tasks

• Design and optimize prompts for LLM-powered enterprise applications.
• Develop system prompts, few-shot examples, tool-use instructions, response formats, and conversation policies.
• Support financial services use cases, including KYC, credit underwriting, sanctions screening, financial crime quality, and customer intelligence.
• Build reusable prompt libraries and templates aligned with enterprise standards and governance requirements.
• Evaluate prompt performance for accuracy, groundedness, hallucination, completeness, safety, latency, and token cost.
• Collaborate with engineering teams on prompt versioning, testing, deployment, and production monitoring.
• Improve RAG quality through retrieval context assessment, chunking, source citations, and response synthesis.
• Conduct adversarial testing for prompt injection, jailbreaks, sensitive-data leakage, and unauthorized tool usage.

Requirements

• Strong understanding of LLMs, prompt engineering, tokenization, context windows, embeddings, and RAG.
• Hands-on experience with OpenAI APIs, Azure OpenAI, AWS Bedrock, Anthropic, or similar platforms.
• Experience with Lang Chain, Llama Index, Semantic Kernel, Copilot Studio, or equivalent tools.
• Strong analytical, troubleshooting, writing, and communication skills.
• Knowledge of prompt security, hallucination mitigation, and enterprise AI governance.
• Ability to develop reusable prompt templates and structured evaluation frameworks.

Schedule

• 4days/week onsite any of the above locations.
• Duration-Full-Time

How to apply

• Share your updated resume or reach out to discuss

Location

• NY/NJ, Tempe, AZ Brea, CA Tampa, FL Los Angeles, CA Walnut Creek, CA