AI Prompt Engineer

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 – where caring and community is in our company DNA, we are always striving to be our best selves and we’re compelled to ask the questions that lead to innovation. As a Managed Services NetSuite Consultant, you will lead and understand a client’s subscription terminology, gather requirements, configure, test, and walk the client through end-to-end processes and train end users. Industry experience in the software and services verticals are preferred. Our team of consultants is a smart and friendly team who enjoy working together in a collaborative and supportive work environment.

Working with Caravel BPM means using your experiences, broadening your skills, and reaching your full potential in work and life—while also making a positive difference for your clients, colleagues, and communities. Our shared entrepreneurial spirit drives us to see and do things differently. Our passion for people makes BPM a place where everyone feels welcome, valued, and part of something bigger. Because People Matter.

BPM India Advisory Service Private Limited – Formerly known as “Burr Pilger Mayer India Private Limited”. (BPM India) is a subsidiary of BPM LLP. Founded in 1986, BPM is one of the largest California-based accounting and consulting firms, ranking in the top 50 in the country. With 17 different office locations, BPM serves emerging and mid-cap businesses as well as high-net-worth individuals in a broad range of industries, including financial services, technology, life science, manufacturing, food, wine and craft brewing, automotive, nonprofits, real estate and construction. The Firm’s International Tax Practice is one of the largest on the West Coast and its well-recognized SEC practice serves approximately 35 public reporting companies, mostly in the technology industry.

Job Summary

As an AI Prompt Engineer at Caravel, you’ll build the production layer of our AI practice — the prompts, prompt chains, and LLM‑driven components that power client solutions and the internal accelerators our consultants rely on. You’ll partner with our AI Specialists to turn solution designs into reliable, evaluated, production‑ready builds. This is a hands‑on build role for someone who cares about getting model behavior right, not just getting it to run.

Key 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 so output quality is measurable and stays stable over time.
• Integrate LLM components with business systems and data — APIs, retrieval/RAG pipelines, and structured outputs.
• Partner with AI Specialists to convert solution designs into production builds, and document patterns for reuse.
• Tune for accuracy, cost, latency, and safety against real evaluation data — not vibes.
• Grow Caravel’s library of reusable AI accelerators.

Preferred Qualifications

• 2+ years building software or AI/LLM components, including hands‑on experience crafting and iterating prompts for real applications.
• Working knowledge of LLM fundamentals: context windows, few‑shot prompting, function/tool calling, structured outputs, and RAG basics.
• Proficiency in Python (or similar) and comfort with APIs, JSON, and version control (Git).
• A test‑and‑measure mindset — you evaluate output quality, you don’t eyeball it.
• Clear written English and strong documentation habits.
• Ability to collaborate across time zones with an onshore/nearshore team.

Preferred Skills

• Experience with evaluation frameworks (e.g., promptfoo, Ragas, or custom eval harnesses).
• Familiarity with embeddings, vector databases, and retrieval pipelines.
• Exposure to ERP/CRM ecosystems (NetSuite, Salesforce) or business‑process automation.
• Experience with agentic frameworks and orchestration.