LLM Prompt Engineer — Production AI Systems

BPM LLP; United States; Remote; USD 110,000 - 170,000; Full time

Job summary

Caravel BPM Technology Solutions is seeking an AI Prompt Engineer to design and build prompts, prompt chains, and LLM-driven components powering client solutions. You will partner with AI Specialists to turn designs into production builds and to create reliable, reusable accelerators.

You’ll work across time zones to implement evaluation harnesses, guardrails, and regression tests, ensuring output quality while optimizing for cost and latency.

Qualifications

• 2+ years building software or AI/LLM components, with hands-on prompts.
• Experience crafting and iterating prompts for real applications.
• Clear written English and strong documentation habits.
• Ability to collaborate across time zones with onshore/nearshore teams.

Responsibilities

• Design, build, test, and iterate on prompts and prompt chains for production LLM workflows across client delivery and internal automation.
• Implement evaluation harnesses, guardrails, and regression tests to ensure output quality.
• Integrate LLM components with business systems via APIs, retrieval/RAG pipelines, and structured outputs.
• Partner with AI specialists to convert designs into production builds and document reusable patterns.
• Tune for accuracy, cost, latency, and safety against real evaluation data.
• Grow Caravel’s library of reusable AI accelerators.

Skills

Prompt engineering

Python

API integration

Documentation

Collaboration across time zones

Testing and evaluation

Education

Tools

Git

APIs

Vector databases

Retrieval pipelines

Job description

Caravel BPM Technology Solutions is seeking an AI Prompt Engineer to design and build prompts, prompt chains, and LLM-driven components powering client solutions. You will partner with AI Specialists to turn designs into production builds and to create reliable, reusable accelerators.

You’ll work across time zones to implement evaluation harnesses, guardrails, and regression tests, ensuring output quality while optimizing for cost and latency.