🛠 Tech Stack

💼 About This Role

You'll design and refine prompts for large language models and multi-modal AI systems at Firework, an AI and video commerce company. You'll serve as the bridge between human intent and machine output, ensuring high-quality, reliable, and ethical AI responses. This role offers the chance to shape agentic commerce at a well-funded, global company.

🎯 What You'll Do

• Develop and curate golden datasets for prompt evaluation and regression testing.
• Design, test, and refine prompts for chat, audio, avatar, and image generation.
• Document best practices and create reusable prompt templates for internal teams.
• Refactor existing prompts to follow best-practice approaches.
• Build and maintain prompt libraries with versioning and metadata tagging.

📋 Requirements

• Bachelor's or Master's degree in STEM or related field.
• Practical experience working with large language models or multi-modal generative models.
• Familiarity with prompt techniques such as zero-shot, few-shot, chain-of-thought.
• Strong analytical and linguistic intuition to translate abstract goals into machine-readable instructions.
• Ability to create and maintain curated evaluation datasets for performance benchmarking.

✨ Nice to Have

• Hands-on experience with Python or another scripting language.
• Experience with LangChain, LangFuse, PromptLayer, or vector search systems.
• Experience designing or working within evaluation pipelines including human and automated evaluations.

🎁 Benefits & Perks

• 🏖️ Remote work from anywhere in Mexico.
• 💰 Competitive compensation with equity.
• 📈 Opportunity to shape cutting-edge AI at a well-funded startup.
• 🏢 Global team with diverse expertise.