Prompt Engineer

Tech9; Ciudad de México; A distancia; MXN 1,468,000 - 2,203,000; Jornada completa

Descripción de la vacante

A forward-thinking technology firm is seeking a Prompt Engineer to design and refine effective prompts for complex LLM production environments. This role requires significant experience in AI and prompt design, targeting innovative learning applications. The position is fully remote for candidates in Mexico and select LATAM countries. Join a mission-driven team to shape the future of AI-driven solutions.

Formación

• 13 years of experience in AI / ML or product-related roles.
• Experience designing prompts in production-grade LLM environments.
• Background in linguistics, psychology, or communication modeling.

Responsabilidades

• Design structure and refine prompts for complex LLM environments.
• Implement and manage retrieval-augmented generation (RAG) pipelines.
• Develop evaluation rubrics and prompt testing datasets.

Conocimientos

Experience in AI / ML

Prompt design expertise

Understanding of RAG architecture

Ability to work in ambiguity

Descripción del empleo

Prompt Engineer

At Tech9 we are driven by a clear vision to empower organizations with AI-centered solutions that make them more adaptable, efficient, and future-ready. As a company at the forefront of innovation we help our clients build exceptional software that not only meets today’s needs but anticipates tomorrow’s challenges.

Our approach blends cutting-edge AI technology, top-tier talent acquisition, and expert project management to ensure that businesses can scale effectively and deliver high-quality world-class software on time and within budget.

Our partnerships speak volumes with clients like Instructure, Young Living, Imagine Learning, Mars Corp. and many others trusting us to lead the way in software development. We are rapidly growing across our offices in the US, LATAM, and India and were creating an environment where talented individuals can thrive, collaborate, and have fun while building transformative solutions.

If you’re excited by the opportunity to work in a fast-paced innovative environment where scaling and building the future of software is key, we’d love to hear from you. Join us as we work together to redefine the world of software development!

Project Overview

We are partnering with a pioneering client at the forefront of immersive learning and AI-powered simulations. Their platform enables professionals to practice and master complex interpersonal skills in high-stakes environments using cutting-edge technology that blends Large Language Models (LLMs), speech recognition, natural language understanding, computer vision, and real-time voice synthesis.

What makes this project unique is its combination of human-in-the-loop orchestration with advanced multi-modal AI systems bringing together live interactions, avatar control, and scalable LLM infrastructure to deliver incredibly lifelike and impactful training experiences. The solution goes far beyond simple chatbot interfaces or single-modal agents.

This is a mission-driven environment backed by research in learning science, psychology, and AI. The goal is to scale this system into a production-grade platform that consistently delivers predictable stable and low-latency GenAI performance. If you’re passionate about building enterprise-level LLM infrastructure working across complex AI systems and helping shape the future of human-AI interaction this is a rare and high-impact opportunity.

Role Overview

We are working with a client who needs a strong Prompt Engineer with a deep understanding of LLM (Large Language Model) systems structured prompt design and simulation-driven learning environments. This role requires a unique blend of product thinking, linguistic strategy, and experience with AI systems in production. You’ll collaborate cross-functionally with simulation designers, AI engineers, and learning architects to create highly structured effective prompts for real-world learning scenarios.

This position is fully remote for candidates based in Colombia, Costa Rica, Mexico, Uruguay, El Salvador or Peru.

Key Responsibilities

• Design structure and refine prompts for complex LLM production environments.
• Implement and manage retrieval-augmented generation (RAG) pipelines using JSON-based structured outputs.
• Develop and maintain evaluation rubrics and prompt testing datasets to measure LLM output quality and alignment.
• Translate abstract learning objectives and human-to-human interaction scenarios into effective prompt-driven AI behavior.
• Act as a strategic liaison between creative simulation teams and technical AI engineers helping ensure narrative fidelity and technical precision.
• Guide the iterative prompt development process from ideation through implementation grounded in psychological and communication-based rubrics.
• Contribute to the evolution of prompt engineering processes, tools, and best practices for scalable production-level deployment.

What You Bring

• 13 years of experience in AI / ML or product-related roles with direct experience working on LLM systems.
• Demonstrated expertise designing prompts in production-grade LLM environments (e.g., OpenAI, Claude, etc.).
• Strong understanding of RAG architecture, evaluation databases, and structured output formats such as JSON.
• Background in linguistics, psychology, learning design, or communication modeling is a strong plus.
• Experience bridging creative and technical domains able to work fluently with both instructional designers and engineers.
• Ability to work in ambiguity, rapidly prototype and refine based on prompt performance data.
• Familiarity with learning experience platforms, human behavior modeling, or communication skill simulations is a bonus.

Nice to Have

• Experience working in simulation platforms, education tech, or virtual learning environments.
• Exposure to psychological rubric design and scenario-based learning journeys.
• Prior collaboration with voice actors, artists, or simulation scriptwriters.

Interview Process

The process is designed to be thoughtful, efficient, and focused on both technical ability and team fit.

• 30-minute on-demand HireVue screening where you’ll respond to situational and behavioral questions to help us understand your ownership mindset, adaptability, and approach to collaboration.
• 10-minute virtual Q&A session with our recruiter to clarify the role and answer any questions you may have. This is not an interview; just a conversation to ensure alignment.
• 15-30 minute interview with Tech9 Hiring Manager.
• 60-minute live technical interview with Head of AI at our client team with a focus on prompt design and work experience.
• 30-minute session with the client’s CTO focused on team fit, technical vision, and your ability to contribute to the long-term goals of the platform.

Total time investment: Approximately 2-3 hours.