Back
Niche AI role but mid-level and metro attracts candidates, moderate competition.
Prompt engineering and LLM integration skills transfer across industries but require ML-specific knowledge.
Requires 2+ years, hands-on LLM/prompt experience and Python, so moderately strict.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design, build, and iterate on production-ready prompts and prompt chains for large language model (LLM) workflows in client delivery and internal automations.
Develop and maintain evaluation mechanisms, guardrails, and regression tests to ensure consistent and measurable output quality over time.
Integrate LLM components with business systems and data sources via APIs and retrieval pipelines; partner with AI Specialists to convert designs into reliable, reusable production builds.
2+ years experience building software or AI/LLM components with hands-on prompt engineering for real applications.
Proficiency in Python or similar languages and familiarity with APIs, JSON, and Git version control.
Working knowledge of LLM fundamentals, including context windows, few-shot prompting, function/tool calling, structured outputs, and retrieval-augmented generation (RAG).
Work Experience Required: Minimum 2 years in relevant AI or software development roles.
Experienced in rigorous test-and-measure approaches to evaluate AI output quality rather than subjective assessment.
Able to collaborate effectively with onshore/nearshore teams across time zones, demonstrating strong documentation and communication skills.
Familiar with evaluation frameworks (e.g., promptfoo, Ragas), embeddings/vector databases, retrieval pipelines, and optionally with ERP/CRM platforms or agentic orchestration frameworks.