Prompt Engineering Architect

This position is posted by Jobgether on behalf of a partner company. We are currently looking for a Prompt Engineering Architect in the United States.

This role is a senior technical leadership position focused on defining how large language model (LLM) systems are designed, evaluated, and scaled across multiple production use cases. You will shape organization-wide standards for prompt design, agentic workflows, and retrieval-augmented generation systems that power real-world applications. The environment is highly technical and innovation-driven, requiring deep expertise in LLM behavior, system architecture, and responsible AI practices. You will collaborate with engineering and applied science teams to translate cutting-edge AI capabilities into reusable frameworks and production-ready solutions. This position blends hands-on architecture work with strategic influence, including mentoring engineers and guiding multi-team adoption of LLM best practices. It is ideal for someone who has shipped LLM-powered products and wants to operate at the intersection of research, engineering, and scalable product design.

• Define organization-wide standards, reference architectures, and reusable design patterns for LLM-powered applications, including prompt structures and agent workflows.
• Design and optimize prompt engineering strategies, instruction templates, and retrieval-augmented generation (RAG) pipelines for production systems.
• Architect advanced agentic systems incorporating planning, tool use, memory, and multi-step reasoning capabilities.
• Develop evaluation frameworks for measuring prompt quality, agent reliability, safety, latency, and end-to-end system performance.
• Build internal tooling, libraries, and frameworks that accelerate LLM application development across multiple engineering teams.
• Establish and enforce guardrails, safety policies, and responsible AI practices for LLM-based systems.
• Conduct technical reviews, lead red-teaming exercises, and mentor engineers on prompt engineering and LLM architecture design.
• Collaborate with model engineering teams on prompt-model co-design, fine-tuning strategies, and system optimization.

Requirements:

• 6+ years of software engineering experience with significant hands-on work in LLM-based or AI-powered systems.
• Proven experience shipping production-grade LLM applications using modern APIs, frameworks, and agent-based architectures.
• Strong expertise in prompt engineering, retrieval-augmented generation (RAG), embeddings, vector databases, and LLM evaluation techniques.
• Advanced Python skills and experience building scalable backend or AI-driven applications.
• Deep understanding of agentic systems, multi-step reasoning, tool use, and orchestration frameworks.
• Experience designing evaluation pipelines for non-deterministic or probabilistic systems.
• Strong knowledge of responsible AI principles, including safety, compliance, and policy enforcement.
• Excellent communication skills with experience mentoring engineers and influencing technical direction.
• Nice to have: experience with fine-tuning workflows, open-source LLM tooling, or enterprise AI integrations.

Benefits:

• Fully remote role within the United States with flexible work arrangements.
• Competitive salary range aligned with experience ($100K–$150K) plus benefits.
• Long-term, stable engagement on production-level AI and LLM architecture projects.
• Opportunity to define foundational standards for LLM engineering across multiple teams.
• High-impact work shaping real-world AI products and enterprise-scale systems.
• Strong technical autonomy with exposure to cutting-edge LLM research and tooling.
• Inclusive and diverse engineering culture with emphasis on innovation and collaboration.