Project Lion – Lead Prompt Engineer – United States (Remote, Part-Time)

About This Opportunity

Our talent team is representing a confidential AI technology organization seeking a Lead Prompt Engineer to guide a specialized team through a full-scale technical migration. This is a remote, part-time role based in the United States, ideal for a senior professional who excels at optimizing large language model performance and mentoring engineering teams.

You'll lead the strategy for transitioning complex template systems to LLM-based evaluation frameworks, using advanced prompt engineering techniques and proprietary tooling to ensure seamless integration and continuous improvement of AI-driven solutions.

Responsibilities

• Utilize automated prompt generation tools to create baseline prompts for complex template architectures
• Run and supervise automated prompt optimization processes, reviewing outputs and identifying optimization plateaus or technical blockers
• Manually design, test, and refine prompts to navigate complex template structures, overcome anti-patterns, and resolve edge cases where automated tooling falls short
• Monitor automated evaluation runs to ensure proper disagreement tracking between human and LLM ratings
• Execute prompt validation against established benchmark data, measuring autorater quality through accuracy metrics including F1 scores, precision, and recall
• Draft technical launch readiness documentation and certification materials for final deployment approval
• Mentor junior prompt engineers and shape team best practices

What We're Looking For

Required Qualifications:

• Native fluency in English
• Must be based in the United States and authorized to work in the U.S.
• Master's or Doctorate degree in Computer Science, Data Science, Computational Linguistics, Human-Computer Interaction, Cognitive Science, or related analytical field
• At least 7 years of experience as a Prompt Engineer
• Proven expertise tuning large language models for structured outputs, complex classification tasks, chain-of-thought reasoning, and few-shot learning approaches
• Strong proficiency in data analysis, error pattern identification, model performance evaluation, and SQL or similar analytics tools
• Technical agility to quickly master proprietary tools with minimal supervision
• Excellent verbal and written communication skills

Preferred Qualifications:

• Experience with enterprise-grade LLM interfaces and APIs
• Background in AI model evaluation, data science, computational linguistics, or software engineering
• Hands-on experience with automated prompt optimization systems or tuning workflows
• Linguistic expertise, including understanding of semantics and logic

How We Work With You

Candidates apply directly through Get A Job.ai. Our recruiting team will screen qualified applicants and coordinate interviews with our client. We handle all communications and offer negotiations on your behalf. Please do not contact the client directly—all applications must come through our platform to be considered.

Federal law requires all new hires to verify identity and work authorization in the United States. Selected candidates will complete required employment eligibility verification, including live video verification with identification documents within the first three days of employment.

Pay

Compensation details will be discussed with qualified candidates during the screening process.

Equal Opportunity: Get A Job.ai is committed to inclusive hiring practices. We welcome applications from candidates of all backgrounds and work with clients who share our commitment to building diverse teams.