[Hiring] AI Prompt Engineer @Zeely Inc.

Role Description

Join us as an AI Engineer (ComfyUI) and become a driving force in scaling Zeely’s LLM initiatives and generative capabilities. We are looking for a specialist who will build a systematic approach to prompt creation and become a key player in the development of our AI platform. You will be responsible for creating scalable templates that work across hundreds of different products, as well as testing new generative models, identifying their use cases, and integrating them into Zeely’s pipelines.

Your key responsibilities:

• Design, build, and continuously optimize complex generative content pipelines across image, video, audio, and text formats.
• Configure and fine-tune generative model parameters to achieve an optimal balance between quality, consistency, and performance.
• Analyze, optimize, and improve existing workflows to increase stability, efficiency, and scalability in production environments.
• Develop and maintain advanced ComfyUI pipelines, including working with custom nodes.
• Proactively troubleshoot generation issues, quickly identifying root causes and implementing effective, long-term fixes.
• Extend and evolve the capabilities of internal generative systems to support new use cases and product needs.
• Collaborate closely with Product and Content teams to translate feature requirements into reliable, production-ready generative solutions.
• Continuously research, benchmark, and test new models and tools, staying on top of market trends and emerging technologies, including: Flux, Nano Banana, OpenAI, Kling AI, Hailuo MiniMax, Veo 3, Runway, Pika Labs.

Qualifications

• 2+ years of hands-on experience in AI / Generative Systems Engineering, with a strong focus on prompt engineering within multi-step, production-grade generative pipelines.
• Practical experience working with generative models across multiple modalities, including: text-to-text, text-to-image, text-to-audio, video-to-video, and others.
• Strong expertise in ComfyUI as a core working environment, including developing custom nodes.
• Deep understanding of the generative AI ecosystem, including model architectures, strengths/limitations, inference behavior, and rapid evaluation of new releases.
• Practical experience integrating open-source models and tools into existing pipelines, including evaluation, optimization, and maintenance.
• Experience designing and configuring LLM-based agents or automation flows (prompt logic, chaining, orchestration, tool usage).
• High adaptability and strong learning velocity — ability to quickly test, validate, and adopt new models, tools, and techniques in a fast-moving AI landscape.
• Strong communication skills, with the ability to collaborate effectively with Product, Content, and Engineering teams, and clearly explain technical constraints and trade-offs.

Requirements

• Nice to have: Experience with an intuitive “vibe coding” approach to content generation.

Benefits

• Work with cutting-edge technologies and contribute to building AI-powered tools.
• Join a strong A-level team of experienced professionals who set a high bar and push each other to do better work.
• Remote-first approach: work from anywhere, with access to our offices in Warsaw and Kyiv.
• We take care of the essentials. Paid time off, sick leaves, and financial support with private entrepreneurship matters.
• Regular performance reviews to ensure your growth is transparent and rewarded.

Recruitment Process

• Intro Call
• Test Task
• Final Interview
• Reference check
• Offer

Send us your CV — we’d love to get to know you better!