Senior AI Agent Engineer

As a Senior AI Agent Engineer, you will build the next generation of agentic AI applications for a creative content generation platform. You will design and develop autonomous AI agents that orchestrate multimodal large language models to generate, evaluate, and refine marketing images, videos, and creative assets at scale.

Key Responsibilities

• Build agentic AI applications using Google Agent Development Kit (ADK), Gemini Agent Platform, and Model Context Protocol (MCP) to automate creative-content workflows.
• Design and implement multimodal AI pipelines using Gemini, Imagen, Veo, and other foundation models for image generation, video creation, and content adaptation.
• Develop evaluation frameworks to measure AI-agent performance, output quality, and reliability across creative-generation tasks.
• Create and manage AI-agent skills, tool integrations, and prompt configurations within the Agent Platform ecosystem.
• Implement function calling, tool use, and structured-output patterns for interaction with enterprise APIs, databases, and external services.
• Build RAG (Retrieval-Augmented Generation) pipelines and context-management systems grounded in brand guidelines, product data, and creative standards.
• Prototype agent architectures, including multi-agent collaboration, graph-based workflows, and human-in-the-loop patterns.
• Instrument agents with structured logging and observability for debugging, performance analysis, and continuous improvement.
• Collaborate with senior engineers and product stakeholders to deliver agent-powered solutions on GCP Cloud Run.

Job Qualifications

• Bachelor’s degree in Computer Science, AI/Machine Learning, Software Engineering, or a related field.
• Demonstrated hands-on experience building AI agents or agentic applications; academic projects, hackathons, personal projects, or internships are accepted.
• Practical knowledge of AI-system design and frameworks.
• Experience implementing multi-agent systems using LangChain, LangGraph, CrewAI, or related tools.
• Practical experience with large language model APIs, such as Gemini, OpenAI, Anthropic, or equivalent, including prompt engineering, function calling, and tool use.
• Familiarity with multimodal AI and with generating or processing images, video, or audio using foundation models.
• Proficiency in Python for building applications, not only notebooks or scripts.
• Understanding of AI evaluation methodologies for measuring the quality, accuracy, and reliability of generative outputs.
• Familiarity with cloud platforms, preferably GCP, and containerized deployments using Docker.
• Strong curiosity, self-directed learning ability, and comfort working with rapidly evolving AI tooling and frameworks.
• Ability to communicate technical concepts clearly and collaborate effectively in a product-driven team.

We Offer

• Large-scale projects and access to IT partners and technologies from day one.
• Training and certification paths for self-development.
• Competitive starting salary and benefits, including private healthcare, stock, savings plans, and sports cards.
• Regular salary increases and promotion opportunities based on results and performance.
• Opportunities to change roles every few years.
• Hybrid work model, with the option to work from home two days per week and work in the office for collaboration.
• Employment is offered exclusively under an Umowa o Pracę (full-time employment contract). Apply only if you agree to these conditions.

Equal Opportunity

Employment decisions are made without discrimination based on race, color, gender, age, national origin, religion, sexual orientation, gender identity or expression, marital status, citizenship, disability, HIV/AIDS status, or any other legally protected factor.