Prompt Engineer — TalentHop, United States

This is a Fully Remote Job

About Our Client:

The organization operates in the technology consulting and software development industry, delivering cloud, AI, data, and enterprise solutions across the United States. It addresses challenges in leveraging large language models (LLMs) and AI-driven applications by providing expertise and scalable architectural solutions.

About the Opportunity:

The PROMPT ENGINEER role is focused on defining and leading strategies, design patterns, and tools for prompt creation, agentic workflows, and LLM-based application architectures within the organization. This position ensures the development of reusable frameworks and tooling that support multiple teams and use cases, contributing to the effective deployment and scaling of LLM-powered products.

Responsibilities:

• Define organization-wide standards, patterns, and reference architectures for LLM applications

• Design prompt structures, instruction templates, and retrieval strategies for production use cases

• Architect agentic systems incorporating tool use, planning, memory, and multi-step reasoning

• Lead design of retrieval-augmented generation pipelines including chunking, indexing, and reranking

• Develop evaluation frameworks for prompt quality, agent reliability, and task success

• Build internal tooling and libraries to accelerate LLM application development

• Establish guardrails, safety filters, and policy enforcement for LLM products

• Collaborate with model engineering teams on prompt-model co-design and fine-tuning

• Conduct technical reviews of LLM application designs across product teams

• Mentor engineers and applied scientists on prompt engineering and LLM architecture

• Lead red-teaming exercises to improve robustness against adversarial inputs

• Track latency, cost, and quality trade-offs and recommend optimizations

• Document patterns, anti-patterns, and lessons learned for internal reuse

• Stay current with LLM capabilities, tooling, and research and translate advances into guidance

Requirements:

• Bachelor’s or Master’s degree in Computer Science, Computational Linguistics, or related field

• 10+ years of software engineering experience including significant LLM application work

• Proven experience shipping LLM-powered products to production

• Deep knowledge of modern LLM APIs and agent frameworks

• Strong understanding of retrieval-augmented generation, embeddings, and vector databases

• Experience designing evaluation pipelines for non-deterministic systems

• Proficiency in Python and modern application frameworks

• Solid understanding of responsible AI principles including safety and policy

• Excellent written and verbal communication skills

• Experience mentoring engineers and influencing technical direction

Pay Range and Compensation Package:

• Salary range is $100,000–$150,000 annually

Equal Opportunity Statement: Our client is an equal opportunity employer. They celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, or national origin.

Note:

TalentHop is a recruitment partner of this role. Please note that all employment decisions, including candidate assessment, interviews, hiring, compensation, and employment terms, are made exclusively by the hiring employer.