AI Prompt Developer

About the role

Caravel is building a new AI practice and needs an AI Prompt Developer to create the production layer of LLM‑driven solutions. You will work closely with AI Specialists to turn designs into reliable, evaluated, production‑ready builds.

Key responsibilities

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

Required profile

• 2+ years of experience building software or AI/LLM components, including hands‑on prompt engineering.
• Working knowledge of LLM fundamentals such as context windows, few‑shot prompting, function/tool calling, structured outputs, and basic RAG.
• Proficiency in Python and comfort with APIs, JSON, and Git version control.
• Test‑and‑measure mindset: you evaluate output quality systematically.
• Strong written English and documentation habits.
• Ability to collaborate across time zones with an on‑shore/near‑shore team.

Required skills

• Python
• APIs
• JSON
• Git
• Prompt engineering
• LLM fundamentals (context windows, few‑shot prompting, function calling)
• Retrieval‑augmented generation (RAG) basics
• Evaluation frameworks (e.g., promptfoo, Ragas) – optional
• Embeddings, vector databases, retrieval pipelines – optional
• NetSuite, Salesforce – optional