AI Prompt Developer

Caravel Partners Llc โ€” Colombia ยท Posted ~1 day ago

Mid Full-time Remote

Skills

Prompt Engineering LLMs Python APIs JSON Git RAG Documentation promptfoo Ragas

๐Ÿ”“ Log in to save this job, tailor your resume & track your apply process โ€” 7 days free, no card needed.

Log in to add to target list

Summary

Build production-ready prompt workflows and AI components, evaluate model quality, integrate language models with business systems, and improve reliable AI automation in a collaborative remote environment.

Highlights

Work remotely while building production AI solutions, shape a growing AI practice, collaborate across time zones, and develop reusable AI capabilities.

Description

Caravel | BPM Technology Solutions AI Prompt Developer AI Practice / Emerging Technology (TSS) ยท Full-time ยท Fully remote โ€” South America ยท Reports to: AI Practice Lead About Caravel Caravel | BPM Technology Solutions is an award-winning NetSuite and Salesforce partner and part of BPM LLP, a Top-40 accounting and advisory firm. For 20+ years and 1,000+ implementations we've helped businesses across North America put the right technology to work โ€” honestly, and without the usual consulting theater. We're a fully remote team with delivery centers across the US, Canada, India, and the Philippines, and we're standing up an AI practice to match. About the role As an AI Prompt Developer at Caravel, you'll build the production layer of our AI practice โ€” 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. What you'll do 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 โ€” 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 โ€” not vibes Grow Caravel's library of reusable AI accelerators What you'll bring 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 โ€” 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 Bonus points 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 Location & schedule Full-time, fully remote within South America, with daily overlap with US business hours to collaborate with the AI Specialist team. Why Caravel You'll help build a brand-new AI practice inside a firm with two decades of delivery credibility โ€” real client problems, real production systems, and a team that would rather tell you the truth than sell you a demo. Compensation & benefits Competitive base commensurate with experience, a fully remote setup, and the opportunity to help shape a new AI practice from the ground up. We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.