MGID is looking for an AI Specialist to join our team. In this creative-technical hybrid role, you will be responsible for both one-off generations and building automated workflows for the scalable creation of text, images, and video. The core expectation is to understand the desired creative outcome and technically assemble the full process—from prompts and models to agent logic and automation.

What You'll Do

Build AI workflows for generating text, images, and video based on input parameters and category requirements.
Combine different models within a single generation process.
Configure agent-based scenarios, branching logic, variation patterns, and rule-driven flows.
Transform individual generation tasks into stable, repeatable, and scalable processes.
Create system prompts, templates, and prompt chains that produce predictable and controlled results.
Understand model limitations and how parameters, context, and API behavior affect output.
Select appropriate model settings for different generation types: textual, visual, and video.
Create and maintain clear input/output formats like JSON and schema-based prompts.
Develop data structures for generation rules, campaign context, and category information.
Use vector stores and RAG approaches to support context-driven generation.
Ensure correct data transfer between models, agents, and automation layers.
Test and compare models for text, image, and multimodal tasks.
Use fine-tuning and LoRA to adapt models to MGID’s specific needs, including dataset preparation.
Evaluate output quality from both technical and creative/advertising perspectives.
Create and implement stability and quality metrics with iterative feedback loops.
Analyze existing workflows to identify high-value automation opportunities.
Build utilities, micro-flows, and automation processes in n8n or other low-code/no-code tools.
Support the deployment of new generation flows to production with the development team.
Create documentation for workflows, prompts, data structures, generation rules, and scenarios.
Document processes and share knowledge with the team.

What We're Looking For

Ability to combine creative understanding of the desired output with technical skills for building AI workflows.
Knowledge of the capabilities, strengths, limitations, and use cases of generative AI models (LLM, image, video) and the ability to select the right approach.
Experience working with LLMs and generative model APIs.
Understanding of prompt logic, instruction structures, and data-driven generation.
Systematic thinking about how model choices and parameters affect creative outcomes.
Ability to assess the quality of visual and textual outputs against advertising requirements.
Effective communication with creative, product, and technical teams.
Basic Python knowledge or ability to work with low-code artifacts by modifying existing fragments.

Nice to Have

Basic understanding of HTML and the ability to make edits.
Experience with SQL, data handling, and integrations.
Experience with AI-IDE tools such as Cursor or Claude Code.
Understanding of AdTech/MarTech and advertising format requirements.

Technical Stack

LLMs
Generative AI models (image, video)
Python
n8n
Low-code/no-code tools
Vector stores
RAG approaches

Team & Environment

You will join a team of over 800 colleagues. You will support the deployment of new generation flows to production together with the development team.