AI Engineer (Image/Video Generation)

Join us as an AI Engineer (Image & Video Generation) and become part of a team building and scaling generative pipelines for next-generation visual content at Zeely.

Zeely AI is a platform that uses artificial intelligence to generate viral UGC videos and ad banners, as well as launch effective ad campaigns on Facebook and Instagram, helping small businesses become visible and scale.

We already have 1mln+ users in the US and are consistently growing more than 4x year-over-year. Today, Zeely is ranked among the Top-3 products in its category on the US market, and our team has grown to over 160 specialists.

Your key responsibilities:

• Design and improve generative pipelines for image and video creation

• Tune and control the behavior of image/video models: visual quality, style consistency, and product identity preservation

• Optimize and scale image→video and text→video workflows for stable and reproducible production results

• Diagnose quality bottlenecks (artifacts, instability, product distortions) and implement fixes

• Extend generative systems for new products and marketing content scenarios

• Research and test new image/video models and tools, staying up to date with the latest industry solutions

What we’re looking for:

• 2+ years of hands-on experience in AI / Generative Systems Engineering, where prompts are part of the engineering logic rather than a standalone artifact

• Strong analytical and formal reasoning skills: ability to build cause-and-effect relationships when diagnosing and optimizing generation systems

• Ability to independently evaluate visual quality of generated outputs: composition, lighting, consistency, and product alignment—without external designer validation. Understanding of UGC/ad content and product-focused generation

• Experience with generative models across multiple modalities: text-to-image, image-to-image, image-to-video, video-to-video, multimodal scenarios

• Experience designing LLM agents or automated generative workflows

• Ability to build complex multi-step workflows, and optimize/debug generation pipelines

• Strong prompt engineering skills for image and video models

• Habit of documenting pipelines, experiments, and decisions: structured notes on models, prompts, parameters, and test results to ensure reproducibility and shared team understanding

• Keeping up with news and releases in image/video generation, understanding the current tooling landscape
  

Nice to have:

• Experience with ComfyUI

• Experience with LoRA tuning or fine-tuning image/video models

• Experience integrating generative pipelines into production systems (APIs, queues, storage, Docker, Kubernetes, etc.)

• Experience building automated workflows in n8n or similar tools

• Practical experience with Python AI/ML libraries

• Experience working with media processing in Python: ffmpeg-python, moviepy, imageio, pydub, and similar tools

Why it’s exciting to work with us:

• Work with cutting-edge technologies and contribute to building AI-powered tools

• Join a strong A-level team that motivates you to grow and achieve more

• Remote-first approach: work from anywhere, with the option to visit our offices in Warsaw and Kyiv

• Paid day offs and sick leaves — we care about your work-life balance

• Regular performance reviews to ensure your growth is transparent and rewarded

• Financial support — consultations for private entrepreneurs from our dedicated finance team

Recruitment process: Intro call > Test Task > Hiring Team Interview > Final Interview > Reference Check > Offer

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